diff --git "a/logs/main/main_log.txt" "b/logs/main/main_log.txt" new file mode 100644--- /dev/null +++ "b/logs/main/main_log.txt" @@ -0,0 +1,8859 @@ +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +WARNING:__main__: +***************************************** +Setting OMP_NUM_THREADS environment variable for each process to be 1 in default, to avoid your system being overloaded, please further tune the variable for optimal performance in your application as needed. +***************************************** +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]: warnings.warn( +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default4]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]: warnings.warn( +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default7]:> setting tensorboard ... +[default0]:using world size: 64, data-parallel-size: 32, tensor-model-parallel size: 2, pipeline-model-parallel size: 1 +[default0]:WARNING: overriding default arguments for tokenizer_type:GPT2BPETokenizer with tokenizer_type:PretrainedFromHF +[default0]:using torch.float16 for parameters ... +[default0]:------------------------ arguments ------------------------ +[default0]: abort_on_unmet_fused_kernel_constraints ......... True +[default0]: accumulate_allreduce_grads_in_fp32 .............. False +[default0]: adam_beta1 ...................................... 0.9 +[default0]: adam_beta2 ...................................... 0.95 +[default0]: adam_eps ........................................ 1e-08 +[default0]: adlr_autoresume ................................. False +[default0]: adlr_autoresume_interval ........................ 1000 +[default0]: apply_query_key_layer_scaling ................... True +[default0]: apply_residual_connection_post_layernorm ........ False +[default0]: attention_dropout ............................... 0.1 +[default0]: attention_softmax_in_fp32 ....................... False +[default0]: bert_binary_head ................................ True +[default0]: bert_load ....................................... None +[default0]: bf16 ............................................ False +[default0]: bias_dropout_fusion ............................. True +[default0]: bias_gelu_fusion ................................ True +[default0]: biencoder_projection_dim ........................ 0 +[default0]: biencoder_shared_query_context_model ............ False +[default0]: block_data_path ................................. None +[default0]: checkpoint_activations .......................... True +[default0]: checkpoint_in_cpu ............................... False +[default0]: checkpoint_num_layers ........................... 1 +[default0]: clip_grad ....................................... 1.0 +[default0]: codecarbon_dir .................................. None +[default0]: consumed_train_samples .......................... 0 +[default0]: consumed_train_tokens ........................... 0 +[default0]: consumed_valid_samples .......................... 0 +[default0]: contigious_checkpointing ........................ False +[default0]: cpu_optimizer ................................... False +[default0]: cpu_torch_adam .................................. False +[default0]: curriculum_learning ............................. False +[default0]: data_impl ....................................... mmap +[default0]: data_parallel_size .............................. 32 +[default0]: data_path ....................................... ['/gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document'] +[default0]: dataloader_type ................................. single +[default0]: DDP_impl ........................................ local +[default0]: decoder_seq_length .............................. None +[default0]: deepscale ....................................... False +[default0]: deepscale_config ................................ None +[default0]: deepspeed ....................................... True +[default0]: deepspeed_activation_checkpointing .............. True +[default0]: deepspeed_config ................................ ./ds_config.1219019.json +[default0]: deepspeed_mpi ................................... False +[default0]: distribute_checkpointed_activations ............. False +[default0]: distributed_backend ............................. nccl +[default0]: embed_layernorm ................................. True +[default0]: embedding_path .................................. None +[default0]: encoder_seq_length .............................. 2048 +[default0]: eod_mask_loss ................................... False +[default0]: eval_interval ................................... 1000 +[default0]: eval_iters ...................................... 1 +[default0]: eval_only ....................................... None +[default0]: evidence_data_path .............................. None +[default0]: exit_duration_in_mins ........................... 1190 +[default0]: exit_interval ................................... None +[default0]: ffn_hidden_size ................................. 10240 +[default0]: finetune ........................................ False +[default0]: fp16 ............................................ True +[default0]: fp16_lm_cross_entropy ........................... False +[default0]: fp32_residual_connection ........................ False +[default0]: gigaflos_no_embeds .............................. 0 +[default0]: global_batch_size ............................... 512 +[default0]: glu_activation .................................. None +[default0]: hidden_dropout .................................. 0.1 +[default0]: hidden_size ..................................... 2560 +[default0]: hysteresis ...................................... 2 +[default0]: ict_head_size ................................... None +[default0]: ict_load ........................................ None +[default0]: img_dim ......................................... 224 +[default0]: indexer_batch_size .............................. 128 +[default0]: indexer_log_interval ............................ 1000 +[default0]: inference ....................................... False +[default0]: init_method_std ................................. 0.1 +[default0]: init_method_xavier_uniform ...................... False +[default0]: initial_loss_scale .............................. 4294967296 +[default0]: kill_switch_path ................................ None +[default0]: kv_channels ..................................... 80 +[default0]: layernorm_epsilon ............................... 1e-05 +[default0]: lazy_mpu_init ................................... None +[default0]: load ............................................ /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]: local_rank ...................................... None +[default0]: log_batch_size_to_tensorboard ................... True +[default0]: log_interval .................................... 1 +[default0]: log_learning_rate_to_tensorboard ................ True +[default0]: log_level ....................................... None +[default0]: log_level_replica ............................... None +[default0]: log_loss_scale_to_tensorboard ................... True +[default0]: log_num_zeros_in_grad ........................... False +[default0]: log_params_norm ................................. False +[default0]: log_path ........................................ None +[default0]: log_timers_to_tensorboard ....................... True +[default0]: log_validation_ppl_to_tensorboard ............... True +[default0]: loss_on_targets_only ............................ False +[default0]: loss_scale ...................................... None +[default0]: loss_scale_window ............................... 1000 +[default0]: lr .............................................. 0.0052 +[default0]: lr_decay_iters .................................. None +[default0]: lr_decay_samples ................................ 1953125 +[default0]: lr_decay_style .................................. cosine +[default0]: lr_decay_tokens ................................. None +[default0]: lr_warmup_fraction .............................. None +[default0]: lr_warmup_iters ................................. 0 +[default0]: lr_warmup_samples ............................... 183105 +[default0]: make_vocab_size_divisible_by .................... 128 +[default0]: mask_prob ....................................... 0.15 +[default0]: masked_softmax_fusion ........................... True +[default0]: max_position_embeddings ......................... 2048 +[default0]: mean_noise_span_length .......................... None +[default0]: memory_centric_tiled_linear ..................... False +[default0]: merge_file ...................................... None +[default0]: micro_batch_size ................................ 16 +[default0]: min_loss_scale .................................. 1.0 +[default0]: min_lr .......................................... 0.0 +[default0]: mmap_warmup ..................................... False +[default0]: mup ............................................. True +[default0]: mup_attn_mult ................................... 10.0 +[default0]: mup_base_ffn_hidden_size ........................ 256 +[default0]: mup_base_hidden_size ............................ 64 +[default0]: mup_coord_check ................................. False +[default0]: mup_input_mult .................................. 10.0 +[default0]: mup_output_mult ................................. 10.0 +[default0]: no_load_optim ................................... None +[default0]: no_load_rng ..................................... None +[default0]: no_save_optim ................................... None +[default0]: no_save_rng ..................................... None +[default0]: noise_density ................................... None +[default0]: num_attention_heads ............................. 32 +[default0]: num_channels .................................... 3 +[default0]: num_classes ..................................... 1000 +[default0]: num_layers ...................................... 32 +[default0]: num_layers_per_virtual_pipeline_stage ........... None +[default0]: num_workers ..................................... 2 +[default0]: onnx_safe ....................................... None +[default0]: openai_gelu ..................................... False +[default0]: optimizer ....................................... adam +[default0]: override_lr_scheduler ........................... False +[default0]: pad_vocab_size_to ............................... 51200 +[default0]: params_dtype .................................... torch.float16 +[default0]: partition_activations ........................... False +[default0]: patch_dim ....................................... 16 +[default0]: pipeline_model_parallel_size .................... 1 +[default0]: position_embedding_type ......................... PositionEmbeddingType.alibi +[default0]: pp_partition_method ............................. type:transformer +[default0]: profile_backward ................................ False +[default0]: query_in_block_prob ............................. 0.1 +[default0]: rampup_batch_size ............................... None +[default0]: rank ............................................ 0 +[default0]: remote_device ................................... none +[default0]: reset_attention_mask ............................ False +[default0]: reset_position_ids .............................. False +[default0]: retriever_report_topk_accuracies ................ [] +[default0]: retriever_score_scaling ......................... False +[default0]: retriever_seq_length ............................ 256 +[default0]: reweight_loss_based_on_position_frequency ....... False +[default0]: sample_rate ..................................... 1.0 +[default0]: save ............................................ /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]: save_interval ................................... 250 +[default0]: scatter_gather_tensors_in_pipeline .............. True +[default0]: scattered_embeddings ............................ False +[default0]: seed ............................................ 42 +[default0]: seq_length ...................................... 2048 +[default0]: sgd_momentum .................................... 0.9 +[default0]: short_seq_prob .................................. 0.1 +[default0]: skip_train_iteration_range ...................... None +[default0]: split ........................................... 969, 30, 1 +[default0]: split_transformers .............................. False +[default0]: sync_tp_duplicated_parameters ................... False +[default0]: synchronize_each_layer .......................... False +[default0]: tensor_model_parallel_size ...................... 2 +[default0]: tensorboard_dir ................................. /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/tr14-2B7-test-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/tensorboard/main +[default0]: tensorboard_log_interval ........................ 1 +[default0]: tensorboard_queue_size .......................... 5 +[default0]: test_weighted_split_names ....................... None +[default0]: test_weighted_split_paths ....................... None +[default0]: test_weighted_split_paths_path .................. None +[default0]: test_weighted_split_splits ...................... None +[default0]: test_weighted_split_weights ..................... None +[default0]: tile_factor ..................................... 1 +[default0]: titles_data_path ................................ None +[default0]: tokenizer_name_or_path .......................... t5-small +[default0]: tokenizer_type .................................. PretrainedFromHF +[default0]: train_iters ..................................... None +[default0]: train_samples ................................... 1953125 +[default0]: train_tokens .................................... None +[default0]: train_weighted_split_paths ...................... None +[default0]: train_weighted_split_paths_path ................. None +[default0]: universal_checkpoint ............................ False +[default0]: use_bnb_optimizer ............................... False +[default0]: use_checkpoint_lr_scheduler ..................... False +[default0]: use_contiguous_buffers_in_ddp ................... False +[default0]: use_cpu_initialization .......................... None +[default0]: use_one_sent_docs ............................... False +[default0]: use_pin_memory .................................. False +[default0]: valid_num_workers ............................... 2 +[default0]: valid_weighted_split_names ...................... None +[default0]: valid_weighted_split_paths ...................... None +[default0]: valid_weighted_split_paths_path ................. None +[default0]: valid_weighted_split_splits ..................... None +[default0]: valid_weighted_split_weights .................... None +[default0]: virtual_pipeline_model_parallel_size ............ None +[default0]: vocab_extra_ids ................................. 0 +[default0]: vocab_file ...................................... None +[default0]: weight_decay .................................... 0.1 +[default0]: world_size ...................................... 64 +[default0]: zero_allgather_bucket_size ...................... 0.0 +[default0]: zero_contigious_gradients ....................... False +[default0]: zero_reduce_bucket_size ......................... 0.0 +[default0]: zero_reduce_scatter ............................. False +[default0]: zero_stage ...................................... 1 +[default0]:-------------------- end of arguments --------------------- +[default0]:setting number of micro-batches to constant 1 +[default0]:> building PretrainedFromHF tokenizer ... +[default0]: vocab file is un-used. loading tokenizer from pre-trained model +[default0]:Offline mode: forcing local_files_only=True +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default6]: warnings.warn( +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default0]:Could not locate the tokenizer configuration file, will try to use the model config instead. +[default0]:Offline mode: forcing local_files_only=True +[default0]:loading configuration file config.json from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/config.json +[default0]:Model config T5Config { +[default0]: "_name_or_path": "t5-small", +[default0]: "architectures": [ +[default0]: "T5ForConditionalGeneration" +[default0]: ], +[default0]: "d_ff": 2048, +[default0]: "d_kv": 64, +[default0]: "d_model": 512, +[default0]: "decoder_start_token_id": 0, +[default0]: "dense_act_fn": "relu", +[default0]: "dropout_rate": 0.1, +[default0]: "eos_token_id": 1, +[default0]: "feed_forward_proj": "relu", +[default0]: "initializer_factor": 1.0, +[default0]: "is_encoder_decoder": true, +[default0]: "is_gated_act": false, +[default0]: "layer_norm_epsilon": 1e-06, +[default0]: "model_type": "t5", +[default0]: "n_positions": 512, +[default0]: "num_decoder_layers": 6, +[default0]: "num_heads": 8, +[default0]: "num_layers": 6, +[default0]: "output_past": true, +[default0]: "pad_token_id": 0, +[default0]: "relative_attention_max_distance": 128, +[default0]: "relative_attention_num_buckets": 32, +[default0]: "task_specific_params": { +[default0]: "summarization": { +[default0]: "early_stopping": true, +[default0]: "length_penalty": 2.0, +[default0]: "max_length": 200, +[default0]: "min_length": 30, +[default0]: "no_repeat_ngram_size": 3, +[default0]: "num_beams": 4, +[default0]: "prefix": "summarize: " +[default0]: }, +[default0]: "translation_en_to_de": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to German: " +[default0]: }, +[default0]: "translation_en_to_fr": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to French: " +[default0]: }, +[default0]: "translation_en_to_ro": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to Romanian: " +[default0]: } +[default0]: }, +[default0]: "transformers_version": "4.25.0.dev0", +[default0]: "use_cache": true, +[default0]: "vocab_size": 32128 +[default0]:} +[default0]: +[default0]:Offline mode: forcing local_files_only=True +[default0]:loading file spiece.model from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/spiece.model +[default0]:loading file tokenizer.json from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/tokenizer.json +[default0]:loading file added_tokens.json from cache at None +[default0]:loading file special_tokens_map.json from cache at None +[default0]:loading file tokenizer_config.json from cache at None +[default0]:loading configuration file config.json from cache at /gpfswork/rech/ajs/commun/models/models--t5-small/snapshots/3479082dc36f8a4730936ef1c9b88cd8b0835c53/config.json +[default0]:Model config T5Config { +[default0]: "_name_or_path": "t5-small", +[default0]: "architectures": [ +[default0]: "T5ForConditionalGeneration" +[default0]: ], +[default0]: "d_ff": 2048, +[default0]: "d_kv": 64, +[default0]: "d_model": 512, +[default0]: "decoder_start_token_id": 0, +[default0]: "dense_act_fn": "relu", +[default0]: "dropout_rate": 0.1, +[default0]: "eos_token_id": 1, +[default0]: "feed_forward_proj": "relu", +[default0]: "initializer_factor": 1.0, +[default0]: "is_encoder_decoder": true, +[default0]: "is_gated_act": false, +[default0]: "layer_norm_epsilon": 1e-06, +[default0]: "model_type": "t5", +[default0]: "n_positions": 512, +[default0]: "num_decoder_layers": 6, +[default0]: "num_heads": 8, +[default0]: "num_layers": 6, +[default0]: "output_past": true, +[default0]: "pad_token_id": 0, +[default0]: "relative_attention_max_distance": 128, +[default0]: "relative_attention_num_buckets": 32, +[default0]: "task_specific_params": { +[default0]: "summarization": { +[default0]: "early_stopping": true, +[default0]: "length_penalty": 2.0, +[default0]: "max_length": 200, +[default0]: "min_length": 30, +[default0]: "no_repeat_ngram_size": 3, +[default0]: "num_beams": 4, +[default0]: "prefix": "summarize: " +[default0]: }, +[default0]: "translation_en_to_de": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to German: " +[default0]: }, +[default0]: "translation_en_to_fr": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to French: " +[default0]: }, +[default0]: "translation_en_to_ro": { +[default0]: "early_stopping": true, +[default0]: "max_length": 300, +[default0]: "num_beams": 4, +[default0]: "prefix": "translate English to Romanian: " +[default0]: } +[default0]: }, +[default0]: "transformers_version": "4.25.0.dev0", +[default0]: "use_cache": true, +[default0]: "vocab_size": 32128 +[default0]:} +[default0]: +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default7]: warnings.warn( +[default0]: > padded vocab (size: 32100) with 19100 dummy tokens (new size: 51200) +[default0]:DeepSpeed general environment info: +[default0]:torch install path ............... ['/gpfswork/rech/six/commun/conda/tr11-176B-ml/lib/python3.8/site-packages/torch'] +[default0]:torch version .................... 1.11.0+cu115 +[default0]:torch cuda version ............... 11.5 +[default0]:torch hip version ................ None +[default0]:nvcc version ..................... 11.4 +[default0]:deepspeed install path ........... ['/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/DeepSpeed/deepspeed'] +[default0]:deepspeed info ................... 0.7.2+2a644488, 2a644488, master +[default0]:deepspeed wheel compiled w. ...... torch 1.11, cuda 11.5 +[default0]:**** Git info for Megatron: git_hash=ef0c6b8 git_branch=mup_integration **** +[default0]:> initializing torch distributed ... +[default0]:[2023-02-16 07:32:10,539] [INFO] [comm.py:633:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default2]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default4]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default5]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default6]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default6]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default6]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default6]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default6]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default6]: warnings.warn( +[default0]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default0]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default0]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default0]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default0]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default0]: warnings.warn( +[default7]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default7]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default7]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default7]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default7]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default7]: warnings.warn( +[default2]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default4]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default2]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default2]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default2]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default2]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default2]: warnings.warn( +[default1]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default1]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default1]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default1]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default5]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default5]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default5]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:/gpfsssd/worksf/projects/rech/six/commun/code/tr11-176B-ml/transformers/src/transformers/models/t5/tokenization_t5_fast.py:155: FutureWarning: This tokenizer was incorrectly instantiated with a model max length of 512 which will be corrected in Transformers v5. +[default5]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default1]: warnings.warn( +[default5]: warnings.warn( +[default3]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default3]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:For now, this behavior is kept to avoid breaking backwards compatibility when padding/encoding with `truncation is True`. +[default4]:- Be aware that you SHOULD NOT rely on t5-small automatically truncating your input to 512 when padding/encoding. +[default4]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default4]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default4]: warnings.warn( +[default3]:- If you want to encode/pad to sequences longer than 512 you can either instantiate this tokenizer with `model_max_length` or pass `max_length` when encoding/padding. +[default3]:- To avoid this warning, please instantiate this tokenizer with `model_max_length` set to your preferred value. +[default3]: warnings.warn( +[default0]:> initializing tensor model parallel with size 2 +[default0]:> initializing pipeline model parallel with size 1 +[default0]:> setting random seeds to 42 ... +[default0]:[2023-02-16 07:32:25,097] [INFO] [checkpointing.py:226:model_parallel_cuda_manual_seed] > initializing model parallel cuda seeds on global rank 0, model parallel rank 0, and data parallel rank 0 with model parallel seed: 2760 and data parallel seed: 42 +[default0]:> compiling dataset index builder ... +[default0]:make: Entering directory '/gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/data' +[default0]:make: Nothing to be done for 'default'. +[default0]:make: Leaving directory '/gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/data' +[default0]:>>> done with dataset index builder. Compilation time: 0.084 seconds +[default0]:> compiling and loading fused kernels ... +[default0]:Detected CUDA files, patching ldflags +[default0]:Emitting ninja build file /gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +[default0]:Building extension module scaled_upper_triang_masked_softmax_cuda... +[default0]:Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +[default0]:ninja: no work to do. +[default0]:Loading extension module scaled_upper_triang_masked_softmax_cuda... +[default0]:Detected CUDA files, patching ldflags +[default0]:Emitting ninja build file /gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +[default0]:Building extension module scaled_masked_softmax_cuda... +[default0]:Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +[default0]:ninja: no work to do. +[default0]:Loading extension module scaled_masked_softmax_cuda... +[default0]:Detected CUDA files, patching ldflags +[default0]:Emitting ninja build file /gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/fused_kernels/build/build.ninja... +[default0]:Building extension module fused_mix_prec_layer_norm_cuda... +[default0]:Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N) +[default0]:ninja: no work to do. +[default0]:Loading extension module fused_mix_prec_layer_norm_cuda... +[default0]:>>> done with compiling and loading fused kernels. Compilation time: 9.443 seconds +[default0]:time to initialize megatron (seconds): 2.626 +[default0]:[after megatron is initialized] datetime: 2023-02-16 07:32:34 +[default0]:building GPT model ... +[default0]:[2023-02-16 07:32:34,707] [INFO] [utils.py:827:see_memory_usage] Before Building Model +[default0]:[2023-02-16 07:32:34,707] [INFO] [utils.py:828:see_memory_usage] MA 0.0 GB Max_MA 0.0 GB CA 0.0 GB Max_CA 0 GB +[default0]:[2023-02-16 07:32:34,708] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 49.51 GB, percent = 9.8% +[default0]:SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +[default0]:Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data=11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63} +[default0]:[2023-02-16 07:32:36,016] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +[default0]:stage=0 layers=41 +[default0]: 0: _to_float16 +[default0]: 1: EmbeddingPipe +[default0]: 2: +[default0]: 3: +[default0]: 4: ParallelTransformerLayerPipe +[default0]: 5: ParallelTransformerLayerPipe +[default0]: 6: ParallelTransformerLayerPipe +[default0]: 7: ParallelTransformerLayerPipe +[default0]: 8: ParallelTransformerLayerPipe +[default0]: 9: ParallelTransformerLayerPipe +[default0]: 10: ParallelTransformerLayerPipe +[default0]: 11: ParallelTransformerLayerPipe +[default0]: 12: ParallelTransformerLayerPipe +[default0]: 13: ParallelTransformerLayerPipe +[default0]: 14: ParallelTransformerLayerPipe +[default0]: 15: ParallelTransformerLayerPipe +[default0]: 16: ParallelTransformerLayerPipe +[default0]: 17: ParallelTransformerLayerPipe +[default0]: 18: ParallelTransformerLayerPipe +[default0]: 19: ParallelTransformerLayerPipe +[default0]: 20: ParallelTransformerLayerPipe +[default0]: 21: ParallelTransformerLayerPipe +[default0]: 22: ParallelTransformerLayerPipe +[default0]: 23: ParallelTransformerLayerPipe +[default0]: 24: ParallelTransformerLayerPipe +[default0]: 25: ParallelTransformerLayerPipe +[default0]: 26: ParallelTransformerLayerPipe +[default0]: 27: ParallelTransformerLayerPipe +[default0]: 28: ParallelTransformerLayerPipe +[default0]: 29: ParallelTransformerLayerPipe +[default0]: 30: ParallelTransformerLayerPipe +[default0]: 31: ParallelTransformerLayerPipe +[default0]: 32: ParallelTransformerLayerPipe +[default0]: 33: ParallelTransformerLayerPipe +[default0]: 34: ParallelTransformerLayerPipe +[default0]: 35: ParallelTransformerLayerPipe +[default0]: 36: undo +[default0]: 37: MixedFusedLayerNorm +[default0]: 38: +[default0]: 39: EmbeddingPipe +[default0]: 40: float16_to_fp32 +[default0]: loss: CrossEntropy +[default0]:[2023-02-16 07:32:36,220] [INFO] [utils.py:827:see_memory_usage] After Building Model +[default0]:[2023-02-16 07:32:36,220] [INFO] [utils.py:828:see_memory_usage] MA 2.56 GB Max_MA 2.56 GB CA 2.62 GB Max_CA 3 GB +[default0]:[2023-02-16 07:32:36,220] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 50.06 GB, percent = 9.9% +[default0]:building GPT model ... +[default0]:[2023-02-16 07:32:36,283] [INFO] [utils.py:827:see_memory_usage] Before Building Model +[default0]:[2023-02-16 07:32:36,284] [INFO] [utils.py:828:see_memory_usage] MA 2.56 GB Max_MA 2.56 GB CA 2.62 GB Max_CA 3 GB +[default0]:[2023-02-16 07:32:36,284] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 50.06 GB, percent = 9.9% +[default0]:SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +[default0]:Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data=11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63} +[default0]:[2023-02-16 07:32:37,594] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +[default0]:stage=0 layers=41 +[default0]: 0: _to_float16 +[default0]: 1: EmbeddingPipe +[default0]: 2: +[default0]: 3: +[default0]: 4: ParallelTransformerLayerPipe +[default0]: 5: ParallelTransformerLayerPipe +[default0]: 6: ParallelTransformerLayerPipe +[default0]: 7: ParallelTransformerLayerPipe +[default0]: 8: ParallelTransformerLayerPipe +[default0]: 9: ParallelTransformerLayerPipe +[default0]: 10: ParallelTransformerLayerPipe +[default0]: 11: ParallelTransformerLayerPipe +[default0]: 12: ParallelTransformerLayerPipe +[default0]: 13: ParallelTransformerLayerPipe +[default0]: 14: ParallelTransformerLayerPipe +[default0]: 15: ParallelTransformerLayerPipe +[default0]: 16: ParallelTransformerLayerPipe +[default0]: 17: ParallelTransformerLayerPipe +[default0]: 18: ParallelTransformerLayerPipe +[default0]: 19: ParallelTransformerLayerPipe +[default0]: 20: ParallelTransformerLayerPipe +[default0]: 21: ParallelTransformerLayerPipe +[default0]: 22: ParallelTransformerLayerPipe +[default0]: 23: ParallelTransformerLayerPipe +[default0]: 24: ParallelTransformerLayerPipe +[default0]: 25: ParallelTransformerLayerPipe +[default0]: 26: ParallelTransformerLayerPipe +[default0]: 27: ParallelTransformerLayerPipe +[default0]: 28: ParallelTransformerLayerPipe +[default0]: 29: ParallelTransformerLayerPipe +[default0]: 30: ParallelTransformerLayerPipe +[default0]: 31: ParallelTransformerLayerPipe +[default0]: 32: ParallelTransformerLayerPipe +[default0]: 33: ParallelTransformerLayerPipe +[default0]: 34: ParallelTransformerLayerPipe +[default0]: 35: ParallelTransformerLayerPipe +[default0]: 36: undo +[default0]: 37: MixedFusedLayerNorm +[default0]: 38: +[default0]: 39: EmbeddingPipe +[default0]: 40: float16_to_fp32 +[default0]: loss: CrossEntropy +[default0]:[2023-02-16 07:32:37,700] [INFO] [utils.py:827:see_memory_usage] After Building Model +[default0]:[2023-02-16 07:32:37,701] [INFO] [utils.py:828:see_memory_usage] MA 2.57 GB Max_MA 2.57 GB CA 2.63 GB Max_CA 3 GB +[default0]:[2023-02-16 07:32:37,701] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 50.08 GB, percent = 10.0% +[default0]:building GPT model ... +[default0]:[2023-02-16 07:32:37,764] [INFO] [utils.py:827:see_memory_usage] Before Building Model +[default0]:[2023-02-16 07:32:37,764] [INFO] [utils.py:828:see_memory_usage] MA 2.57 GB Max_MA 2.57 GB CA 2.63 GB Max_CA 3 GB +[default0]:[2023-02-16 07:32:37,764] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 50.08 GB, percent = 10.0% +[default0]:SEED_LAYERS=False BASE_SEED=1234 SEED_FN=None +[default0]:Using topology: {ProcessCoord(pipe=0, data=0, model=0): 0, ProcessCoord(pipe=0, data=0, model=1): 1, ProcessCoord(pipe=0, data=1, model=0): 2, ProcessCoord(pipe=0, data=1, model=1): 3, ProcessCoord(pipe=0, data=2, model=0): 4, ProcessCoord(pipe=0, data=2, model=1): 5, ProcessCoord(pipe=0, data=3, model=0): 6, ProcessCoord(pipe=0, data=3, model=1): 7, ProcessCoord(pipe=0, data=4, model=0): 8, ProcessCoord(pipe=0, data=4, model=1): 9, ProcessCoord(pipe=0, data=5, model=0): 10, ProcessCoord(pipe=0, data=5, model=1): 11, ProcessCoord(pipe=0, data=6, model=0): 12, ProcessCoord(pipe=0, data=6, model=1): 13, ProcessCoord(pipe=0, data=7, model=0): 14, ProcessCoord(pipe=0, data=7, model=1): 15, ProcessCoord(pipe=0, data=8, model=0): 16, ProcessCoord(pipe=0, data=8, model=1): 17, ProcessCoord(pipe=0, data=9, model=0): 18, ProcessCoord(pipe=0, data=9, model=1): 19, ProcessCoord(pipe=0, data=10, model=0): 20, ProcessCoord(pipe=0, data=10, model=1): 21, ProcessCoord(pipe=0, data=11, model=0): 22, ProcessCoord(pipe=0, data=11, model=1): 23, ProcessCoord(pipe=0, data=12, model=0): 24, ProcessCoord(pipe=0, data=12, model=1): 25, ProcessCoord(pipe=0, data=13, model=0): 26, ProcessCoord(pipe=0, data=13, model=1): 27, ProcessCoord(pipe=0, data=14, model=0): 28, ProcessCoord(pipe=0, data=14, model=1): 29, ProcessCoord(pipe=0, data=15, model=0): 30, ProcessCoord(pipe=0, data=15, model=1): 31, ProcessCoord(pipe=0, data=16, model=0): 32, ProcessCoord(pipe=0, data=16, model=1): 33, ProcessCoord(pipe=0, data=17, model=0): 34, ProcessCoord(pipe=0, data=17, model=1): 35, ProcessCoord(pipe=0, data=18, model=0): 36, ProcessCoord(pipe=0, data=18, model=1): 37, ProcessCoord(pipe=0, data=19, model=0): 38, ProcessCoord(pipe=0, data=19, model=1): 39, ProcessCoord(pipe=0, data=20, model=0): 40, ProcessCoord(pipe=0, data=20, model=1): 41, ProcessCoord(pipe=0, data=21, model=0): 42, ProcessCoord(pipe=0, data=21, model=1): 43, ProcessCoord(pipe=0, data=22, model=0): 44, ProcessCoord(pipe=0, data=22, model=1): 45, ProcessCoord(pipe=0, data=23, model=0): 46, ProcessCoord(pipe=0, data=23, model=1): 47, ProcessCoord(pipe=0, data=24, model=0): 48, ProcessCoord(pipe=0, data=24, model=1): 49, ProcessCoord(pipe=0, data=25, model=0): 50, ProcessCoord(pipe=0, data=25, model=1): 51, ProcessCoord(pipe=0, data=26, model=0): 52, ProcessCoord(pipe=0, data=26, model=1): 53, ProcessCoord(pipe=0, data=27, model=0): 54, ProcessCoord(pipe=0, data=27, model=1): 55, ProcessCoord(pipe=0, data=28, model=0): 56, ProcessCoord(pipe=0, data=28, model=1): 57, ProcessCoord(pipe=0, data=29, model=0): 58, ProcessCoord(pipe=0, data=29, model=1): 59, ProcessCoord(pipe=0, data=30, model=0): 60, ProcessCoord(pipe=0, data=30, model=1): 61, ProcessCoord(pipe=0, data=31, model=0): 62, ProcessCoord(pipe=0, data=31, model=1): 63} +[default0]:[2023-02-16 07:32:39,075] [INFO] [module.py:366:_partition_layers] Partitioning pipeline stages with method type:transformer +[default0]:stage=0 layers=41 +[default0]: 0: _to_float16 +[default0]: 1: EmbeddingPipe +[default0]: 2: +[default0]: 3: +[default0]: 4: ParallelTransformerLayerPipe +[default0]: 5: ParallelTransformerLayerPipe +[default0]: 6: ParallelTransformerLayerPipe +[default0]: 7: ParallelTransformerLayerPipe +[default0]: 8: ParallelTransformerLayerPipe +[default0]: 9: ParallelTransformerLayerPipe +[default0]: 10: ParallelTransformerLayerPipe +[default0]: 11: ParallelTransformerLayerPipe +[default0]: 12: ParallelTransformerLayerPipe +[default0]: 13: ParallelTransformerLayerPipe +[default0]: 14: ParallelTransformerLayerPipe +[default0]: 15: ParallelTransformerLayerPipe +[default0]: 16: ParallelTransformerLayerPipe +[default0]: 17: ParallelTransformerLayerPipe +[default0]: 18: ParallelTransformerLayerPipe +[default0]: 19: ParallelTransformerLayerPipe +[default0]: 20: ParallelTransformerLayerPipe +[default0]: 21: ParallelTransformerLayerPipe +[default0]: 22: ParallelTransformerLayerPipe +[default0]: 23: ParallelTransformerLayerPipe +[default0]: 24: ParallelTransformerLayerPipe +[default0]: 25: ParallelTransformerLayerPipe +[default0]: 26: ParallelTransformerLayerPipe +[default0]: 27: ParallelTransformerLayerPipe +[default0]: 28: ParallelTransformerLayerPipe +[default0]: 29: ParallelTransformerLayerPipe +[default0]: 30: ParallelTransformerLayerPipe +[default0]: 31: ParallelTransformerLayerPipe +[default0]: 32: ParallelTransformerLayerPipe +[default0]: 33: ParallelTransformerLayerPipe +[default0]: 34: ParallelTransformerLayerPipe +[default0]: 35: ParallelTransformerLayerPipe +[default0]: 36: undo +[default0]: 37: MixedFusedLayerNorm +[default0]: 38: +[default0]: 39: EmbeddingPipe +[default0]: 40: float16_to_fp32 +[default0]: loss: CrossEntropy +[default0]:[2023-02-16 07:32:39,188] [INFO] [utils.py:827:see_memory_usage] After Building Model +[default0]:[2023-02-16 07:32:39,188] [INFO] [utils.py:828:see_memory_usage] MA 2.59 GB Max_MA 2.59 GB CA 2.66 GB Max_CA 3 GB +[default0]:[2023-02-16 07:32:39,188] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 50.09 GB, percent = 10.0% +[default0]:setting training iterations to 3814 +[default0]:> learning rate decay style: cosine +[default0]:DeepSpeed is enabled. +[default0]:[2023-02-16 07:32:39,225] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed info: version=0.7.2+2a644488, git-hash=2a644488, git-branch=master +[default0]:[2023-02-16 07:32:42,159] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False +[default0]:[2023-02-16 07:32:42,160] [INFO] [logging.py:68:log_dist] [Rank 0] Removing param_group that has no 'params' in the client Optimizer +[default0]:[2023-02-16 07:32:42,160] [INFO] [logging.py:68:log_dist] [Rank 0] Using client Optimizer as basic optimizer +[default0]:[2023-02-16 07:32:42,174] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Basic Optimizer = {basic_optimizer.__class__.__name__} +[default0]:[2023-02-16 07:32:42,174] [INFO] [utils.py:52:is_zero_supported_optimizer] Checking ZeRO support for optimizer=FusedAdam type= +[default0]:[2023-02-16 07:32:42,174] [INFO] [logging.py:68:log_dist] [Rank 0] Creating fp16 ZeRO stage 1 optimizer +[default0]:[2023-02-16 07:32:42,175] [INFO] [stage_1_and_2.py:134:__init__] Reduce bucket size 500000000 +[default0]:[2023-02-16 07:32:42,175] [INFO] [stage_1_and_2.py:135:__init__] Allgather bucket size 500000000 +[default0]:[2023-02-16 07:32:42,175] [INFO] [stage_1_and_2.py:136:__init__] CPU Offload: False +[default0]:[2023-02-16 07:32:42,175] [INFO] [stage_1_and_2.py:137:__init__] Round robin gradient partitioning: False +[default3]:Rank: 27 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 23 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 53 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 35 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 37 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 5 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 49 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 1 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 51 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 3 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 45 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 47 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 33 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 57 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 63 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 59 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 29 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 43 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 61 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 11 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 0 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 41 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 25 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 17 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 34 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 16 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 52 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 20 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 26 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 28 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 4 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 2 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 12 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 55 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default1]:Rank: 9 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default3]:Rank: 19 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 21 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 42 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 56 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 46 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 24 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 58 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 50 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 62 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 8 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 48 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 15 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 60 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default5]:Rank: 13 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 54 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 40 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 7 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 39 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 18 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 44 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 22 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:Rank: 32 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 38 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default4]:Rank: 36 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 6 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default2]:Rank: 10 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 14 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default7]:Rank: 31 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default6]:Rank: 30 partition count [32, 32, 32, 32, 32, 32] and sizes[(4915200, False), (14336000, False), (2048000, False), (15155200, False), (4915200, False), (24640, False)] +[default0]:[2023-02-16 07:32:46,323] [INFO] [utils.py:827:see_memory_usage] Before initializing optimizer states +[default0]:[2023-02-16 07:32:46,323] [INFO] [utils.py:828:see_memory_usage] MA 2.66 GB Max_MA 2.69 GB CA 5.17 GB Max_CA 5 GB +[default0]:[2023-02-16 07:32:46,324] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 65.14 GB, percent = 12.9% +[default0]:[2023-02-16 07:32:46,432] [INFO] [utils.py:827:see_memory_usage] After initializing optimizer states +[default0]:[2023-02-16 07:32:46,432] [INFO] [utils.py:828:see_memory_usage] MA 2.96 GB Max_MA 3.12 GB CA 5.5 GB Max_CA 6 GB +[default0]:[2023-02-16 07:32:46,432] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 65.14 GB, percent = 12.9% +[default0]:[2023-02-16 07:32:46,432] [INFO] [stage_1_and_2.py:516:__init__] optimizer state initialized +[default0]:[2023-02-16 07:32:46,494] [INFO] [utils.py:827:see_memory_usage] After initializing ZeRO optimizer +[default0]:[2023-02-16 07:32:46,494] [INFO] [utils.py:828:see_memory_usage] MA 2.96 GB Max_MA 2.96 GB CA 5.5 GB Max_CA 6 GB +[default0]:[2023-02-16 07:32:46,494] [INFO] [utils.py:836:see_memory_usage] CPU Virtual Memory: used = 65.15 GB, percent = 12.9% +[default0]:[2023-02-16 07:32:46,494] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed Final Optimizer = FusedAdam +[default0]:[2023-02-16 07:32:46,495] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed using client LR scheduler +[default0]:[2023-02-16 07:32:46,495] [INFO] [logging.py:68:log_dist] [Rank 0] DeepSpeed LR Scheduler = +[default0]:[2023-02-16 07:32:46,495] [INFO] [logging.py:68:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0, 0.0, 0.0, 0.0, 0.0, 0.0], mom=[(0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95)] +[default0]:[2023-02-16 07:32:46,495] [INFO] [config.py:987:print] DeepSpeedEngine configuration: +[default0]:[2023-02-16 07:32:46,495] [INFO] [config.py:991:print] activation_checkpointing_config { +[default0]: "partition_activations": false, +[default0]: "contiguous_memory_optimization": false, +[default0]: "cpu_checkpointing": false, +[default0]: "number_checkpoints": null, +[default0]: "synchronize_checkpoint_boundary": false, +[default0]: "profile": false +[default0]:} +[default0]:[2023-02-16 07:32:46,495] [INFO] [config.py:991:print] aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True} +[default0]:[2023-02-16 07:32:46,495] [INFO] [config.py:991:print] amp_enabled .................. False +[default0]:[2023-02-16 07:32:46,495] [INFO] [config.py:991:print] amp_params ................... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] autotuning_config ............ { +[default0]: "enabled": false, +[default0]: "start_step": null, +[default0]: "end_step": null, +[default0]: "metric_path": null, +[default0]: "arg_mappings": null, +[default0]: "metric": "throughput", +[default0]: "model_info": null, +[default0]: "results_dir": null, +[default0]: "exps_dir": null, +[default0]: "overwrite": true, +[default0]: "fast": true, +[default0]: "start_profile_step": 3, +[default0]: "end_profile_step": 5, +[default0]: "tuner_type": "gridsearch", +[default0]: "tuner_early_stopping": 5, +[default0]: "tuner_num_trials": 50, +[default0]: "model_info_path": null, +[default0]: "mp_size": 1, +[default0]: "max_train_batch_size": null, +[default0]: "min_train_batch_size": 1, +[default0]: "max_train_micro_batch_size_per_gpu": 1.024000e+03, +[default0]: "min_train_micro_batch_size_per_gpu": 1, +[default0]: "num_tuning_micro_batch_sizes": 3 +[default0]:} +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] bfloat16_enabled ............. False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] checkpoint_tag_validation_enabled True +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] checkpoint_tag_validation_fail False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] comms_config ................. +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] communication_data_type ...... None +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991: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}} +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] curriculum_enabled ........... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] curriculum_params ............ False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] dataloader_drop_last ......... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] disable_allgather ............ False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] dump_state ................... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] dynamic_loss_scale_args ...... {'init_scale': 4096, 'scale_window': 500, 'delayed_shift': 2, 'min_scale': 1} +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_enabled ........... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_gas_boundary_resolution 1 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_layer_name ........ bert.encoder.layer +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_layer_num ......... 0 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_max_iter .......... 100 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_stability ......... 1e-06 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_tol ............... 0.01 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] eigenvalue_verbose ........... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] elasticity_enabled ........... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] flops_profiler_config ........ { +[default0]: "enabled": false, +[default0]: "profile_step": 1, +[default0]: "module_depth": -1, +[default0]: "top_modules": 1, +[default0]: "detailed": true, +[default0]: "output_file": null +[default0]:} +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] fp16_auto_cast ............... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] fp16_enabled ................. True +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] fp16_master_weights_and_gradients False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] global_rank .................. 0 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] gradient_accumulation_steps .. 1 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] gradient_clipping ............ 1.0 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] gradient_predivide_factor .... 1.0 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] initial_dynamic_scale ........ 4096 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] load_universal_checkpoint .... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] loss_scale ................... 0 +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] memory_breakdown ............. False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] monitor_config ............... +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] nebula_config ................ { +[default0]: "enabled": false, +[default0]: "persistent_storage_path": null, +[default0]: "persistent_time_interval": 100, +[default0]: "num_of_version_in_retention": 2, +[default0]: "enable_nebula_load": true, +[default0]: "load_path": null +[default0]:} +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] optimizer_legacy_fusion ...... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] optimizer_name ............... None +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] optimizer_params ............. None +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0} +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] pld_enabled .................. False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] pld_params ................... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] prescale_gradients ........... False +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] scheduler_name ............... None +[default0]:[2023-02-16 07:32:46,496] [INFO] [config.py:991:print] scheduler_params ............. None +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] sparse_attention ............. None +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] sparse_gradients_enabled ..... False +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] steps_per_print .............. 2000 +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] train_batch_size ............. 512 +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] train_micro_batch_size_per_gpu 16 +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] wall_clock_breakdown ......... False +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] world_size ................... 32 +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] zero_allow_untested_optimizer False +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] zero_config .................. stage=1 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=500000000 allgather_partitions=True allgather_bucket_size=500000000 overlap_comm=False load_from_fp32_weights=True elastic_checkpoint=False offload_param=None offload_optimizer=None sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=50000000 param_persistence_threshold=100000 model_persistence_threshold=9223372036854775807 max_live_parameters=1000000000 max_reuse_distance=1000000000 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 +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] zero_enabled ................. True +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:991:print] zero_optimization_stage ...... 1 +[default0]:[2023-02-16 07:32:46,497] [INFO] [config.py:976:print_user_config] json = { +[default0]: "train_micro_batch_size_per_gpu": 16, +[default0]: "train_batch_size": 512, +[default0]: "gradient_clipping": 1.0, +[default0]: "zero_optimization": { +[default0]: "stage": 1 +[default0]: }, +[default0]: "fp16": { +[default0]: "enabled": true, +[default0]: "loss_scale": 0, +[default0]: "loss_scale_window": 500, +[default0]: "hysteresis": 2, +[default0]: "min_loss_scale": 1, +[default0]: "initial_scale_power": 12 +[default0]: }, +[default0]: "steps_per_print": 2.000000e+03, +[default0]: "wall_clock_breakdown": false +[default0]:} +[default0]:[2023-02-16 07:32:46,497] [INFO] [engine.py:87:__init__] CONFIG: micro_batches=1 micro_batch_size=16 +[default1]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:time (ms) | load-checkpoint: 21.92 +[default2]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,794] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,795] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,796] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,794] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,772] [INFO] [engine.py:145:__init__] RANK=1 STAGE=0 LAYERS=41 [0, 41) STAGE_PARAMS=1324615680 (1324.616M) TOTAL_PARAMS=2649231360 (2649.231M) UNIQUE_PARAMS=2649231360 (2649.231M) +[default1]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,792] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,794] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,772] [INFO] [engine.py:145:__init__] RANK=0 STAGE=0 LAYERS=41 [0, 41) STAGE_PARAMS=1324615680 (1324.616M) TOTAL_PARAMS=2649231360 (2649.231M) UNIQUE_PARAMS=2649231360 (2649.231M) +[default0]:[2023-02-16 07:32:46,793] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:WARNING: could not find the metadata file /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]: will not load any checkpoints and will start from random +[default7]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default1]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default2]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default7]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,780] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default3]:[2023-02-16 07:32:46,790] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default4]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default5]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,791] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default6]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:[2023-02-16 07:32:46,798] [WARNING] [engine.py:2574:load_checkpoint] Unable to find latest file at /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/latest, if trying to load latest checkpoint please ensure this file exists or pass an explicit checkpoint tag when loading a checkpoint. +[default0]:/gpfsdswork/projects/rech/ajs/commun/code/Megatron-DeepSpeed/megatron/utils.py:349: UserWarning: Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings +[default0]: warnings.warn("Parameter count with the embeddings will be inaccurate with PP > 1, as the first and last stage hold several copies of the embeddings") +[default0]:estimated model parameters: 2.64923136 +[default0]:estimated model parameters without embeddings: 2.51815936 +[default0]:[after model, optimizer, and learning rate scheduler are built] datetime: 2023-02-16 07:32:47 +[default0]:> building train, validation, and test datasets ... +[default0]: > datasets target sizes (minimum size): +[default0]: train: 1953125 +[default0]: validation: 2048 +[default0]: test: 512 +[default0]:> building train, validation, and test datasets for GPT ... +[default0]: > building dataset index ... +[default0]: reading sizes... +[default0]: reading pointers... +[default0]: reading document index... +[default0]: creating numpy buffer of mmap... +[default0]: creating memory view of numpy buffer... +[default0]: > finished creating indexed dataset in 0.021607 seconds +[default0]: number of documents: 364868892 +[default0]: > dataset split: +[default0]: train: +[default0]: document indices in [0, 353557956) total of 353557956 documents +[default0]: validation: +[default0]: document indices in [353557956, 364504023) total of 10946067 documents +[default0]: test: +[default0]: document indices in [364504023, 364868892) total of 364869 documents +[default0]: > loading doc-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_train_indexmap_1953125ns_2048sl_42s_doc_idx.npy +[default0]: > loading sample-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_train_indexmap_1953125ns_2048sl_42s_sample_idx.npy +[default0]: > loading shuffle-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_train_indexmap_1953125ns_2048sl_42s_shuffle_idx.npy +[default0]: loaded indexed file in 0.046 seconds +[default0]: total number of samples: 82627993 +[default0]: total number of epochs: 1 +[default0]: > loading doc-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_valid_indexmap_2048ns_2048sl_42s_doc_idx.npy +[default0]: > loading sample-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_valid_indexmap_2048ns_2048sl_42s_sample_idx.npy +[default0]: > loading shuffle-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_valid_indexmap_2048ns_2048sl_42s_shuffle_idx.npy +[default0]: loaded indexed file in 0.037 seconds +[default0]: total number of samples: 2558380 +[default0]: total number of epochs: 1 +[default0]: > loading doc-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_test_indexmap_512ns_2048sl_42s_doc_idx.npy +[default0]: > loading sample-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_test_indexmap_512ns_2048sl_42s_sample_idx.npy +[default0]: > loading shuffle-idx mapping from /gpfsscratch/rech/ajs/commun/datasets/c4/gpt2tok_c4_text_document_test_indexmap_512ns_2048sl_42s_shuffle_idx.npy +[default0]: loaded indexed file in 0.010 seconds +[default0]: total number of samples: 84955 +[default0]: total number of epochs: 1 +[default0]:> finished creating GPT datasets ... +[default7]:time (ms) | model-and-optimizer-setup: 12354.13 | train/valid/test-data-iterators-setup: 7119.57 +[default0]:[after dataloaders are built] datetime: 2023-02-16 07:32:56 +[default0]:done with setup ... +[default0]:training ... +[default0]:Number of parameters: [tensor rank - pipeline rank] w/ and w/o embeddings: +[default0]:[000-000] 2.6492B / 2.5182B +[default1]:[001-000] 2.6492B / 2.5182B +[default0]:[before the start of training step] datetime: 2023-02-16 07:32:56 +[default0]:[2023-02-16 07:32:57,009] [INFO] [checkpointing.py:547:forward] Activation Checkpointing Information +[default0]:[2023-02-16 07:32:57,010] [INFO] [checkpointing.py:548:forward] ----Partition Activations False, CPU CHECKPOINTING False +[default0]:[2023-02-16 07:32:57,010] [INFO] [checkpointing.py:551:forward] ----contiguous Memory Checkpointing False with 32 total layers +[default0]:[2023-02-16 07:32:57,010] [INFO] [checkpointing.py:554:forward] ----Synchronization False +[default0]:[2023-02-16 07:32:57,010] [INFO] [checkpointing.py:555:forward] ----Profiling time in checkpointing False +[default1]:[Rank 1] (after 1 iterations) memory (MB) | allocated: 6264.68505859375 | max allocated: 20970.4296875 | reserved: 24998.0 | max reserved: 24998.0 +[default7]: iteration 1/ 3814 | consumed samples: 512 | consumed tokens: 1048576 | elapsed time per iteration (s): 6.45 | learning rate: 1.454E-06 | global batch size: 512 | lm loss: 1.084328E+01 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 79.387 | TFLOPs: 59.96 | +[default0]:[Rank 0] (after 1 iterations) memory (MB) | allocated: 6240.66552734375 | max allocated: 20946.41015625 | reserved: 24996.0 | max reserved: 24996.0 +[default7]: iteration 2/ 3814 | consumed samples: 1024 | consumed tokens: 2097152 | elapsed time per iteration (s): 6.02 | learning rate: 2.908E-06 | global batch size: 512 | lm loss: 1.084320E+01 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.059 | TFLOPs: 64.25 | +[default7]: iteration 3/ 3814 | consumed samples: 1536 | consumed tokens: 3145728 | elapsed time per iteration (s): 5.87 | learning rate: 4.362E-06 | global batch size: 512 | lm loss: 1.084305E+01 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.175 | TFLOPs: 65.84 | +[default7]: iteration 4/ 3814 | consumed samples: 2048 | consumed tokens: 4194304 | elapsed time per iteration (s): 6.03 | learning rate: 5.816E-06 | global batch size: 512 | lm loss: 1.084150E+01 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.956 | TFLOPs: 64.17 | +[default7]: iteration 5/ 3814 | consumed samples: 2560 | consumed tokens: 5242880 | elapsed time per iteration (s): 5.87 | learning rate: 7.270E-06 | global batch size: 512 | lm loss: 1.083579E+01 | loss scale: 4096.0 | grad norm: 0.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.205 | TFLOPs: 65.87 | +[default7]: iteration 6/ 3814 | consumed samples: 3072 | consumed tokens: 6291456 | elapsed time per iteration (s): 5.94 | learning rate: 8.724E-06 | global batch size: 512 | lm loss: 1.083183E+01 | loss scale: 4096.0 | grad norm: 0.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.215 | TFLOPs: 65.12 | +[default7]: iteration 7/ 3814 | consumed samples: 3584 | consumed tokens: 7340032 | elapsed time per iteration (s): 5.85 | learning rate: 1.018E-05 | global batch size: 512 | lm loss: 1.081935E+01 | loss scale: 4096.0 | grad norm: 0.070 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.481 | TFLOPs: 66.08 | +[default7]: iteration 8/ 3814 | consumed samples: 4096 | consumed tokens: 8388608 | elapsed time per iteration (s): 6.03 | learning rate: 1.163E-05 | global batch size: 512 | lm loss: 1.081121E+01 | loss scale: 4096.0 | grad norm: 0.059 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.875 | TFLOPs: 64.11 | +[default7]: iteration 9/ 3814 | consumed samples: 4608 | consumed tokens: 9437184 | elapsed time per iteration (s): 5.96 | learning rate: 1.309E-05 | global batch size: 512 | lm loss: 1.080503E+01 | loss scale: 4096.0 | grad norm: 0.051 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.857 | TFLOPs: 64.85 | +[default7]: iteration 10/ 3814 | consumed samples: 5120 | consumed tokens: 10485760 | elapsed time per iteration (s): 5.91 | learning rate: 1.454E-05 | global batch size: 512 | lm loss: 1.079703E+01 | loss scale: 4096.0 | grad norm: 0.045 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.614 | TFLOPs: 65.42 | +[default7]: iteration 11/ 3814 | consumed samples: 5632 | consumed tokens: 11534336 | elapsed time per iteration (s): 5.94 | learning rate: 1.599E-05 | global batch size: 512 | lm loss: 1.079229E+01 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.189 | TFLOPs: 65.10 | +[default7]: iteration 12/ 3814 | consumed samples: 6144 | consumed tokens: 12582912 | elapsed time per iteration (s): 6.00 | learning rate: 1.745E-05 | global batch size: 512 | lm loss: 1.078737E+01 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.309 | TFLOPs: 64.43 | +[default7]: iteration 13/ 3814 | consumed samples: 6656 | consumed tokens: 13631488 | elapsed time per iteration (s): 5.95 | learning rate: 1.890E-05 | global batch size: 512 | lm loss: 1.078162E+01 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.043 | TFLOPs: 64.99 | +[default7]: iteration 14/ 3814 | consumed samples: 7168 | consumed tokens: 14680064 | elapsed time per iteration (s): 5.97 | learning rate: 2.036E-05 | global batch size: 512 | lm loss: 1.077581E+01 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.831 | TFLOPs: 64.83 | +[default7]: iteration 15/ 3814 | consumed samples: 7680 | consumed tokens: 15728640 | elapsed time per iteration (s): 5.84 | learning rate: 2.181E-05 | global batch size: 512 | lm loss: 1.077175E+01 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.706 | TFLOPs: 66.25 | +[default7]: iteration 16/ 3814 | consumed samples: 8192 | consumed tokens: 16777216 | elapsed time per iteration (s): 5.88 | learning rate: 2.326E-05 | global batch size: 512 | lm loss: 1.076675E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.099 | TFLOPs: 65.79 | +[default7]: iteration 17/ 3814 | consumed samples: 8704 | consumed tokens: 17825792 | elapsed time per iteration (s): 6.04 | learning rate: 2.472E-05 | global batch size: 512 | lm loss: 1.076239E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.838 | TFLOPs: 64.08 | +[default7]: iteration 18/ 3814 | consumed samples: 9216 | consumed tokens: 18874368 | elapsed time per iteration (s): 5.92 | learning rate: 2.617E-05 | global batch size: 512 | lm loss: 1.075810E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.550 | TFLOPs: 65.37 | +[default7]: iteration 19/ 3814 | consumed samples: 9728 | consumed tokens: 19922944 | elapsed time per iteration (s): 5.91 | learning rate: 2.763E-05 | global batch size: 512 | lm loss: 1.075457E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.599 | TFLOPs: 65.41 | +[default7]: iteration 20/ 3814 | consumed samples: 10240 | consumed tokens: 20971520 | elapsed time per iteration (s): 5.92 | learning rate: 2.908E-05 | global batch size: 512 | lm loss: 1.075031E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.489 | TFLOPs: 65.33 | +[default7]: iteration 21/ 3814 | consumed samples: 10752 | consumed tokens: 22020096 | elapsed time per iteration (s): 5.96 | learning rate: 3.053E-05 | global batch size: 512 | lm loss: 1.074698E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.920 | TFLOPs: 64.90 | +[default7]: iteration 22/ 3814 | consumed samples: 11264 | consumed tokens: 23068672 | elapsed time per iteration (s): 5.81 | learning rate: 3.199E-05 | global batch size: 512 | lm loss: 1.074316E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.090 | TFLOPs: 66.53 | +[default7]: iteration 23/ 3814 | consumed samples: 11776 | consumed tokens: 24117248 | elapsed time per iteration (s): 5.89 | learning rate: 3.344E-05 | global batch size: 512 | lm loss: 1.073942E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.936 | TFLOPs: 65.66 | +[default7]: iteration 24/ 3814 | consumed samples: 12288 | consumed tokens: 25165824 | elapsed time per iteration (s): 5.99 | learning rate: 3.490E-05 | global batch size: 512 | lm loss: 1.073511E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.518 | TFLOPs: 64.59 | +[default7]: iteration 25/ 3814 | consumed samples: 12800 | consumed tokens: 26214400 | elapsed time per iteration (s): 6.00 | learning rate: 3.635E-05 | global batch size: 512 | lm loss: 1.073186E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.321 | TFLOPs: 64.44 | +[default7]: iteration 26/ 3814 | consumed samples: 13312 | consumed tokens: 27262976 | elapsed time per iteration (s): 5.92 | learning rate: 3.780E-05 | global batch size: 512 | lm loss: 1.072695E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.484 | TFLOPs: 65.32 | +[default7]: iteration 27/ 3814 | consumed samples: 13824 | consumed tokens: 28311552 | elapsed time per iteration (s): 5.93 | learning rate: 3.926E-05 | global batch size: 512 | lm loss: 1.072351E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.313 | TFLOPs: 65.19 | +[default7]: iteration 28/ 3814 | consumed samples: 14336 | consumed tokens: 29360128 | elapsed time per iteration (s): 5.96 | learning rate: 4.071E-05 | global batch size: 512 | lm loss: 1.072010E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.971 | TFLOPs: 64.94 | +[default7]: iteration 29/ 3814 | consumed samples: 14848 | consumed tokens: 30408704 | elapsed time per iteration (s): 5.89 | learning rate: 4.217E-05 | global batch size: 512 | lm loss: 1.071557E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.934 | TFLOPs: 65.66 | +[default7]: iteration 30/ 3814 | consumed samples: 15360 | consumed tokens: 31457280 | elapsed time per iteration (s): 6.02 | learning rate: 4.362E-05 | global batch size: 512 | lm loss: 1.071051E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.091 | TFLOPs: 64.27 | +[default7]: iteration 31/ 3814 | consumed samples: 15872 | consumed tokens: 32505856 | elapsed time per iteration (s): 5.91 | learning rate: 4.507E-05 | global batch size: 512 | lm loss: 1.070650E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.623 | TFLOPs: 65.43 | +[default7]: iteration 32/ 3814 | consumed samples: 16384 | consumed tokens: 33554432 | elapsed time per iteration (s): 5.85 | learning rate: 4.653E-05 | global batch size: 512 | lm loss: 1.070108E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.478 | TFLOPs: 66.07 | +[default7]: iteration 33/ 3814 | consumed samples: 16896 | consumed tokens: 34603008 | elapsed time per iteration (s): 5.91 | learning rate: 4.798E-05 | global batch size: 512 | lm loss: 1.069613E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.697 | TFLOPs: 65.48 | +[default7]: iteration 34/ 3814 | consumed samples: 17408 | consumed tokens: 35651584 | elapsed time per iteration (s): 5.86 | learning rate: 4.944E-05 | global batch size: 512 | lm loss: 1.069110E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.342 | TFLOPs: 65.97 | +[default7]: iteration 35/ 3814 | consumed samples: 17920 | consumed tokens: 36700160 | elapsed time per iteration (s): 5.92 | learning rate: 5.089E-05 | global batch size: 512 | lm loss: 1.068486E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.478 | TFLOPs: 65.32 | +[default7]: iteration 36/ 3814 | consumed samples: 18432 | consumed tokens: 37748736 | elapsed time per iteration (s): 5.93 | learning rate: 5.235E-05 | global batch size: 512 | lm loss: 1.067876E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.280 | TFLOPs: 65.17 | +[default7]: iteration 37/ 3814 | consumed samples: 18944 | consumed tokens: 38797312 | elapsed time per iteration (s): 5.94 | learning rate: 5.380E-05 | global batch size: 512 | lm loss: 1.067301E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.144 | TFLOPs: 65.07 | +[default7]: iteration 38/ 3814 | consumed samples: 19456 | consumed tokens: 39845888 | elapsed time per iteration (s): 5.87 | learning rate: 5.525E-05 | global batch size: 512 | lm loss: 1.066552E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.208 | TFLOPs: 65.87 | +[default7]: iteration 39/ 3814 | consumed samples: 19968 | consumed tokens: 40894464 | elapsed time per iteration (s): 5.92 | learning rate: 5.671E-05 | global batch size: 512 | lm loss: 1.065996E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.553 | TFLOPs: 65.37 | +[default7]: iteration 40/ 3814 | consumed samples: 20480 | consumed tokens: 41943040 | elapsed time per iteration (s): 5.92 | learning rate: 5.816E-05 | global batch size: 512 | lm loss: 1.065252E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.501 | TFLOPs: 65.34 | +[default7]: iteration 41/ 3814 | consumed samples: 20992 | consumed tokens: 42991616 | elapsed time per iteration (s): 5.80 | learning rate: 5.962E-05 | global batch size: 512 | lm loss: 1.064403E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.295 | TFLOPs: 66.69 | +[default7]: iteration 42/ 3814 | consumed samples: 21504 | consumed tokens: 44040192 | elapsed time per iteration (s): 5.96 | learning rate: 6.107E-05 | global batch size: 512 | lm loss: 1.063731E+01 | loss scale: 4096.0 | grad norm: 0.018 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.969 | TFLOPs: 64.93 | +[default7]: iteration 43/ 3814 | consumed samples: 22016 | consumed tokens: 45088768 | elapsed time per iteration (s): 5.87 | learning rate: 6.252E-05 | global batch size: 512 | lm loss: 1.062888E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.268 | TFLOPs: 65.91 | +[default7]: iteration 44/ 3814 | consumed samples: 22528 | consumed tokens: 46137344 | elapsed time per iteration (s): 5.98 | learning rate: 6.398E-05 | global batch size: 512 | lm loss: 1.062197E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.603 | TFLOPs: 64.66 | +[default7]: iteration 45/ 3814 | consumed samples: 23040 | consumed tokens: 47185920 | elapsed time per iteration (s): 5.92 | learning rate: 6.543E-05 | global batch size: 512 | lm loss: 1.061328E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.487 | TFLOPs: 65.32 | +[default7]: iteration 46/ 3814 | consumed samples: 23552 | consumed tokens: 48234496 | elapsed time per iteration (s): 5.92 | learning rate: 6.689E-05 | global batch size: 512 | lm loss: 1.060473E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.530 | TFLOPs: 65.36 | +[default7]: iteration 47/ 3814 | consumed samples: 24064 | consumed tokens: 49283072 | elapsed time per iteration (s): 5.91 | learning rate: 6.834E-05 | global batch size: 512 | lm loss: 1.059578E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.602 | TFLOPs: 65.41 | +[default7]: iteration 48/ 3814 | consumed samples: 24576 | consumed tokens: 50331648 | elapsed time per iteration (s): 5.58 | learning rate: 6.979E-05 | global batch size: 512 | lm loss: 1.058728E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.712 | TFLOPs: 69.27 | +[default7]: iteration 49/ 3814 | consumed samples: 25088 | consumed tokens: 51380224 | elapsed time per iteration (s): 5.61 | learning rate: 7.125E-05 | global batch size: 512 | lm loss: 1.057781E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.198 | TFLOPs: 68.88 | +[default7]: iteration 50/ 3814 | consumed samples: 25600 | consumed tokens: 52428800 | elapsed time per iteration (s): 5.62 | learning rate: 7.270E-05 | global batch size: 512 | lm loss: 1.056925E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.147 | TFLOPs: 68.84 | +[default7]: iteration 51/ 3814 | consumed samples: 26112 | consumed tokens: 53477376 | elapsed time per iteration (s): 5.90 | learning rate: 7.416E-05 | global batch size: 512 | lm loss: 1.055953E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.726 | TFLOPs: 65.50 | +[default7]: iteration 52/ 3814 | consumed samples: 26624 | consumed tokens: 54525952 | elapsed time per iteration (s): 5.92 | learning rate: 7.561E-05 | global batch size: 512 | lm loss: 1.055021E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.455 | TFLOPs: 65.30 | +[default7]: iteration 53/ 3814 | consumed samples: 27136 | consumed tokens: 55574528 | elapsed time per iteration (s): 5.88 | learning rate: 7.706E-05 | global batch size: 512 | lm loss: 1.054025E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.006 | TFLOPs: 65.72 | +[default7]: iteration 54/ 3814 | consumed samples: 27648 | consumed tokens: 56623104 | elapsed time per iteration (s): 5.82 | learning rate: 7.852E-05 | global batch size: 512 | lm loss: 1.053020E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.013 | TFLOPs: 66.48 | +[default7]: iteration 55/ 3814 | consumed samples: 28160 | consumed tokens: 57671680 | elapsed time per iteration (s): 5.91 | learning rate: 7.997E-05 | global batch size: 512 | lm loss: 1.052120E+01 | loss scale: 4096.0 | grad norm: 0.019 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.575 | TFLOPs: 65.39 | +[default7]: iteration 56/ 3814 | consumed samples: 28672 | consumed tokens: 58720256 | elapsed time per iteration (s): 5.93 | learning rate: 8.143E-05 | global batch size: 512 | lm loss: 1.050866E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.398 | TFLOPs: 65.26 | +[default7]: iteration 57/ 3814 | consumed samples: 29184 | consumed tokens: 59768832 | elapsed time per iteration (s): 5.90 | learning rate: 8.288E-05 | global batch size: 512 | lm loss: 1.049788E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.717 | TFLOPs: 65.50 | +[default7]: iteration 58/ 3814 | consumed samples: 29696 | consumed tokens: 60817408 | elapsed time per iteration (s): 5.90 | learning rate: 8.433E-05 | global batch size: 512 | lm loss: 1.048628E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.839 | TFLOPs: 65.59 | +[default7]: iteration 59/ 3814 | consumed samples: 30208 | consumed tokens: 61865984 | elapsed time per iteration (s): 5.90 | learning rate: 8.579E-05 | global batch size: 512 | lm loss: 1.047457E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.707 | TFLOPs: 65.49 | +[default7]: iteration 60/ 3814 | consumed samples: 30720 | consumed tokens: 62914560 | elapsed time per iteration (s): 5.92 | learning rate: 8.724E-05 | global batch size: 512 | lm loss: 1.046392E+01 | loss scale: 4096.0 | grad norm: 0.020 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.452 | TFLOPs: 65.30 | +[default7]: iteration 61/ 3814 | consumed samples: 31232 | consumed tokens: 63963136 | elapsed time per iteration (s): 5.91 | learning rate: 8.870E-05 | global batch size: 512 | lm loss: 1.045185E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.706 | TFLOPs: 65.49 | +[default7]: iteration 62/ 3814 | consumed samples: 31744 | consumed tokens: 65011712 | elapsed time per iteration (s): 5.91 | learning rate: 9.015E-05 | global batch size: 512 | lm loss: 1.044118E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.624 | TFLOPs: 65.43 | +[default7]: iteration 63/ 3814 | consumed samples: 32256 | consumed tokens: 66060288 | elapsed time per iteration (s): 5.87 | learning rate: 9.160E-05 | global batch size: 512 | lm loss: 1.042539E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.185 | TFLOPs: 65.85 | +[default7]: iteration 64/ 3814 | consumed samples: 32768 | consumed tokens: 67108864 | elapsed time per iteration (s): 5.91 | learning rate: 9.306E-05 | global batch size: 512 | lm loss: 1.041560E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.669 | TFLOPs: 65.46 | +[default7]: iteration 65/ 3814 | consumed samples: 33280 | consumed tokens: 68157440 | elapsed time per iteration (s): 5.92 | learning rate: 9.451E-05 | global batch size: 512 | lm loss: 1.040460E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.518 | TFLOPs: 65.35 | +[default7]: iteration 66/ 3814 | consumed samples: 33792 | consumed tokens: 69206016 | elapsed time per iteration (s): 5.91 | learning rate: 9.597E-05 | global batch size: 512 | lm loss: 1.039090E+01 | loss scale: 4096.0 | grad norm: 0.021 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.580 | TFLOPs: 65.39 | +[default7]: iteration 67/ 3814 | consumed samples: 34304 | consumed tokens: 70254592 | elapsed time per iteration (s): 5.87 | learning rate: 9.742E-05 | global batch size: 512 | lm loss: 1.037729E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.154 | TFLOPs: 65.83 | +[default7]: iteration 68/ 3814 | consumed samples: 34816 | consumed tokens: 71303168 | elapsed time per iteration (s): 5.93 | learning rate: 9.887E-05 | global batch size: 512 | lm loss: 1.036336E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.393 | TFLOPs: 65.25 | +[default7]: iteration 69/ 3814 | consumed samples: 35328 | consumed tokens: 72351744 | elapsed time per iteration (s): 5.88 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 1.034778E+01 | loss scale: 4096.0 | grad norm: 0.022 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.099 | TFLOPs: 65.79 | +[default7]: iteration 70/ 3814 | consumed samples: 35840 | consumed tokens: 73400320 | elapsed time per iteration (s): 5.94 | learning rate: 1.018E-04 | global batch size: 512 | lm loss: 1.033869E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.141 | TFLOPs: 65.06 | +[default7]: iteration 71/ 3814 | consumed samples: 36352 | consumed tokens: 74448896 | elapsed time per iteration (s): 5.87 | learning rate: 1.032E-04 | global batch size: 512 | lm loss: 1.032406E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.155 | TFLOPs: 65.83 | +[default7]: iteration 72/ 3814 | consumed samples: 36864 | consumed tokens: 75497472 | elapsed time per iteration (s): 5.87 | learning rate: 1.047E-04 | global batch size: 512 | lm loss: 1.030879E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.163 | TFLOPs: 65.83 | +[default7]: iteration 73/ 3814 | consumed samples: 37376 | consumed tokens: 76546048 | elapsed time per iteration (s): 5.95 | learning rate: 1.061E-04 | global batch size: 512 | lm loss: 1.029210E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.094 | TFLOPs: 65.03 | +[default7]: iteration 74/ 3814 | consumed samples: 37888 | consumed tokens: 77594624 | elapsed time per iteration (s): 5.60 | learning rate: 1.076E-04 | global batch size: 512 | lm loss: 1.028033E+01 | loss scale: 4096.0 | grad norm: 0.023 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.386 | TFLOPs: 69.03 | +[default7]: iteration 75/ 3814 | consumed samples: 38400 | consumed tokens: 78643200 | elapsed time per iteration (s): 5.84 | learning rate: 1.091E-04 | global batch size: 512 | lm loss: 1.026290E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.739 | TFLOPs: 66.27 | +[default7]: iteration 76/ 3814 | consumed samples: 38912 | consumed tokens: 79691776 | elapsed time per iteration (s): 5.90 | learning rate: 1.105E-04 | global batch size: 512 | lm loss: 1.025037E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.781 | TFLOPs: 65.55 | +[default7]: iteration 77/ 3814 | consumed samples: 39424 | consumed tokens: 80740352 | elapsed time per iteration (s): 5.92 | learning rate: 1.120E-04 | global batch size: 512 | lm loss: 1.023584E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.542 | TFLOPs: 65.37 | +[default7]: iteration 78/ 3814 | consumed samples: 39936 | consumed tokens: 81788928 | elapsed time per iteration (s): 5.91 | learning rate: 1.134E-04 | global batch size: 512 | lm loss: 1.021865E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.584 | TFLOPs: 65.40 | +[default7]: iteration 79/ 3814 | consumed samples: 40448 | consumed tokens: 82837504 | elapsed time per iteration (s): 5.92 | learning rate: 1.149E-04 | global batch size: 512 | lm loss: 1.020329E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.446 | TFLOPs: 65.29 | +[default7]: iteration 80/ 3814 | consumed samples: 40960 | consumed tokens: 83886080 | elapsed time per iteration (s): 5.93 | learning rate: 1.163E-04 | global batch size: 512 | lm loss: 1.018869E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.351 | TFLOPs: 65.22 | +[default7]: iteration 81/ 3814 | consumed samples: 41472 | consumed tokens: 84934656 | elapsed time per iteration (s): 5.92 | learning rate: 1.178E-04 | global batch size: 512 | lm loss: 1.017031E+01 | loss scale: 4096.0 | grad norm: 0.024 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.425 | TFLOPs: 65.28 | +[default7]: iteration 82/ 3814 | consumed samples: 41984 | consumed tokens: 85983232 | elapsed time per iteration (s): 5.93 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 1.015755E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.271 | TFLOPs: 65.16 | +[default7]: iteration 83/ 3814 | consumed samples: 42496 | consumed tokens: 87031808 | elapsed time per iteration (s): 5.95 | learning rate: 1.207E-04 | global batch size: 512 | lm loss: 1.013700E+01 | loss scale: 4096.0 | grad norm: 0.025 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.058 | TFLOPs: 65.00 | +[default7]: iteration 84/ 3814 | consumed samples: 43008 | consumed tokens: 88080384 | elapsed time per iteration (s): 5.85 | learning rate: 1.221E-04 | global batch size: 512 | lm loss: 1.011769E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.459 | TFLOPs: 66.06 | +[default7]: iteration 85/ 3814 | consumed samples: 43520 | consumed tokens: 89128960 | elapsed time per iteration (s): 5.86 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 1.010938E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.335 | TFLOPs: 65.97 | +[default7]: iteration 86/ 3814 | consumed samples: 44032 | consumed tokens: 90177536 | elapsed time per iteration (s): 5.93 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 1.008603E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.368 | TFLOPs: 65.23 | +[default7]: iteration 87/ 3814 | consumed samples: 44544 | consumed tokens: 91226112 | elapsed time per iteration (s): 5.92 | learning rate: 1.265E-04 | global batch size: 512 | lm loss: 1.007291E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.512 | TFLOPs: 65.34 | +[default7]: iteration 88/ 3814 | consumed samples: 45056 | consumed tokens: 92274688 | elapsed time per iteration (s): 5.90 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 1.005318E+01 | loss scale: 4096.0 | grad norm: 0.026 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.822 | TFLOPs: 65.58 | +[default7]: iteration 89/ 3814 | consumed samples: 45568 | consumed tokens: 93323264 | elapsed time per iteration (s): 5.86 | learning rate: 1.294E-04 | global batch size: 512 | lm loss: 1.003179E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.432 | TFLOPs: 66.04 | +[default7]: iteration 90/ 3814 | consumed samples: 46080 | consumed tokens: 94371840 | elapsed time per iteration (s): 5.88 | learning rate: 1.309E-04 | global batch size: 512 | lm loss: 1.001447E+01 | loss scale: 4096.0 | grad norm: 0.027 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.094 | TFLOPs: 65.78 | +[default7]: iteration 91/ 3814 | consumed samples: 46592 | consumed tokens: 95420416 | elapsed time per iteration (s): 5.88 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 1.000058E+01 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.129 | TFLOPs: 65.81 | +[default7]: iteration 92/ 3814 | consumed samples: 47104 | consumed tokens: 96468992 | elapsed time per iteration (s): 5.90 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 9.980034E+00 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.770 | TFLOPs: 65.54 | +[default7]: iteration 93/ 3814 | consumed samples: 47616 | consumed tokens: 97517568 | elapsed time per iteration (s): 5.89 | learning rate: 1.352E-04 | global batch size: 512 | lm loss: 9.960077E+00 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.948 | TFLOPs: 65.67 | +[default7]: iteration 94/ 3814 | consumed samples: 48128 | consumed tokens: 98566144 | elapsed time per iteration (s): 5.93 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 9.941378E+00 | loss scale: 4096.0 | grad norm: 0.028 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.292 | TFLOPs: 65.18 | +[default7]: iteration 95/ 3814 | consumed samples: 48640 | consumed tokens: 99614720 | elapsed time per iteration (s): 5.92 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 9.927045E+00 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.453 | TFLOPs: 65.30 | +[default7]: iteration 96/ 3814 | consumed samples: 49152 | consumed tokens: 100663296 | elapsed time per iteration (s): 5.92 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 9.902261E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.431 | TFLOPs: 65.28 | +[default7]: iteration 97/ 3814 | consumed samples: 49664 | consumed tokens: 101711872 | elapsed time per iteration (s): 5.87 | learning rate: 1.410E-04 | global batch size: 512 | lm loss: 9.886023E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.182 | TFLOPs: 65.85 | +[default7]: iteration 98/ 3814 | consumed samples: 50176 | consumed tokens: 102760448 | elapsed time per iteration (s): 5.84 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 9.864664E+00 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.718 | TFLOPs: 66.25 | +[default7]: iteration 99/ 3814 | consumed samples: 50688 | consumed tokens: 103809024 | elapsed time per iteration (s): 5.85 | learning rate: 1.439E-04 | global batch size: 512 | lm loss: 9.846703E+00 | loss scale: 4096.0 | grad norm: 0.029 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.534 | TFLOPs: 66.12 | +[default7]: iteration 100/ 3814 | consumed samples: 51200 | consumed tokens: 104857600 | elapsed time per iteration (s): 5.98 | learning rate: 1.454E-04 | global batch size: 512 | lm loss: 9.829114E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.687 | TFLOPs: 64.72 | +[default7]: iteration 101/ 3814 | consumed samples: 51712 | consumed tokens: 105906176 | elapsed time per iteration (s): 5.93 | learning rate: 1.469E-04 | global batch size: 512 | lm loss: 9.809166E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.410 | TFLOPs: 65.27 | +[default7]: iteration 102/ 3814 | consumed samples: 52224 | consumed tokens: 106954752 | elapsed time per iteration (s): 5.88 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 9.786610E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.060 | TFLOPs: 65.76 | +[default7]: iteration 103/ 3814 | consumed samples: 52736 | consumed tokens: 108003328 | elapsed time per iteration (s): 5.89 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 9.758693E+00 | loss scale: 4096.0 | grad norm: 0.030 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.934 | TFLOPs: 65.66 | +[default7]: iteration 104/ 3814 | consumed samples: 53248 | consumed tokens: 109051904 | elapsed time per iteration (s): 5.92 | learning rate: 1.512E-04 | global batch size: 512 | lm loss: 9.742516E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.494 | TFLOPs: 65.33 | +[default7]: iteration 105/ 3814 | consumed samples: 53760 | consumed tokens: 110100480 | elapsed time per iteration (s): 5.90 | learning rate: 1.527E-04 | global batch size: 512 | lm loss: 9.722271E+00 | loss scale: 4096.0 | grad norm: 0.031 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.725 | TFLOPs: 65.50 | +[default7]: iteration 106/ 3814 | consumed samples: 54272 | consumed tokens: 111149056 | elapsed time per iteration (s): 5.82 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 9.700767E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.961 | TFLOPs: 66.44 | +[default7]: iteration 107/ 3814 | consumed samples: 54784 | consumed tokens: 112197632 | elapsed time per iteration (s): 5.86 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 9.680296E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.406 | TFLOPs: 66.02 | +[default7]: iteration 108/ 3814 | consumed samples: 55296 | consumed tokens: 113246208 | elapsed time per iteration (s): 5.96 | learning rate: 1.570E-04 | global batch size: 512 | lm loss: 9.662853E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.865 | TFLOPs: 64.85 | +[default7]: iteration 109/ 3814 | consumed samples: 55808 | consumed tokens: 114294784 | elapsed time per iteration (s): 5.90 | learning rate: 1.585E-04 | global batch size: 512 | lm loss: 9.631208E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.767 | TFLOPs: 65.54 | +[default7]: iteration 110/ 3814 | consumed samples: 56320 | consumed tokens: 115343360 | elapsed time per iteration (s): 5.84 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 9.623828E+00 | loss scale: 4096.0 | grad norm: 0.032 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.733 | TFLOPs: 66.27 | +[default7]: iteration 111/ 3814 | consumed samples: 56832 | consumed tokens: 116391936 | elapsed time per iteration (s): 5.86 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 9.593485E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.418 | TFLOPs: 66.03 | +[default7]: iteration 112/ 3814 | consumed samples: 57344 | consumed tokens: 117440512 | elapsed time per iteration (s): 5.87 | learning rate: 1.629E-04 | global batch size: 512 | lm loss: 9.573215E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.165 | TFLOPs: 65.84 | +[default7]: iteration 113/ 3814 | consumed samples: 57856 | consumed tokens: 118489088 | elapsed time per iteration (s): 5.98 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 9.549521E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.603 | TFLOPs: 64.66 | +[default7]: iteration 114/ 3814 | consumed samples: 58368 | consumed tokens: 119537664 | elapsed time per iteration (s): 5.97 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 9.529623E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.698 | TFLOPs: 64.73 | +[default7]: iteration 115/ 3814 | consumed samples: 58880 | consumed tokens: 120586240 | elapsed time per iteration (s): 5.86 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 9.511297E+00 | loss scale: 4096.0 | grad norm: 0.033 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.343 | TFLOPs: 65.97 | +[default7]: iteration 116/ 3814 | consumed samples: 59392 | consumed tokens: 121634816 | elapsed time per iteration (s): 5.96 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 9.494873E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.860 | TFLOPs: 64.85 | +[default7]: iteration 117/ 3814 | consumed samples: 59904 | consumed tokens: 122683392 | elapsed time per iteration (s): 5.94 | learning rate: 1.701E-04 | global batch size: 512 | lm loss: 9.458460E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.170 | TFLOPs: 65.09 | +[default7]: iteration 118/ 3814 | consumed samples: 60416 | consumed tokens: 123731968 | elapsed time per iteration (s): 5.88 | learning rate: 1.716E-04 | global batch size: 512 | lm loss: 9.438057E+00 | loss scale: 4096.0 | grad norm: 0.034 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.110 | TFLOPs: 65.80 | +[default7]: iteration 119/ 3814 | consumed samples: 60928 | consumed tokens: 124780544 | elapsed time per iteration (s): 5.91 | learning rate: 1.730E-04 | global batch size: 512 | lm loss: 9.412538E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.667 | TFLOPs: 65.46 | +[default7]: iteration 120/ 3814 | consumed samples: 61440 | consumed tokens: 125829120 | elapsed time per iteration (s): 5.92 | learning rate: 1.745E-04 | global batch size: 512 | lm loss: 9.392351E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.553 | TFLOPs: 65.37 | +[default7]: iteration 121/ 3814 | consumed samples: 61952 | consumed tokens: 126877696 | elapsed time per iteration (s): 5.92 | learning rate: 1.759E-04 | global batch size: 512 | lm loss: 9.365488E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.428 | TFLOPs: 65.28 | +[default7]: iteration 122/ 3814 | consumed samples: 62464 | consumed tokens: 127926272 | elapsed time per iteration (s): 5.97 | learning rate: 1.774E-04 | global batch size: 512 | lm loss: 9.346395E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.720 | TFLOPs: 64.75 | +[default7]: iteration 123/ 3814 | consumed samples: 62976 | consumed tokens: 128974848 | elapsed time per iteration (s): 5.96 | learning rate: 1.788E-04 | global batch size: 512 | lm loss: 9.323269E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.902 | TFLOPs: 64.88 | +[default7]: iteration 124/ 3814 | consumed samples: 63488 | consumed tokens: 130023424 | elapsed time per iteration (s): 5.90 | learning rate: 1.803E-04 | global batch size: 512 | lm loss: 9.300753E+00 | loss scale: 4096.0 | grad norm: 0.035 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.796 | TFLOPs: 65.56 | +[default7]: iteration 125/ 3814 | consumed samples: 64000 | consumed tokens: 131072000 | elapsed time per iteration (s): 5.91 | learning rate: 1.818E-04 | global batch size: 512 | lm loss: 9.280002E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.695 | TFLOPs: 65.48 | +[default7]: iteration 126/ 3814 | consumed samples: 64512 | consumed tokens: 132120576 | elapsed time per iteration (s): 5.94 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 9.246640E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.130 | TFLOPs: 65.05 | +[default7]: iteration 127/ 3814 | consumed samples: 65024 | consumed tokens: 133169152 | elapsed time per iteration (s): 5.90 | learning rate: 1.847E-04 | global batch size: 512 | lm loss: 9.231417E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.833 | TFLOPs: 65.59 | +[default7]: iteration 128/ 3814 | consumed samples: 65536 | consumed tokens: 134217728 | elapsed time per iteration (s): 6.00 | learning rate: 1.861E-04 | global batch size: 512 | lm loss: 9.212619E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.322 | TFLOPs: 64.44 | +[default7]: iteration 129/ 3814 | consumed samples: 66048 | consumed tokens: 135266304 | elapsed time per iteration (s): 5.91 | learning rate: 1.876E-04 | global batch size: 512 | lm loss: 9.180699E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.683 | TFLOPs: 65.47 | +[default7]: iteration 130/ 3814 | consumed samples: 66560 | consumed tokens: 136314880 | elapsed time per iteration (s): 5.93 | learning rate: 1.890E-04 | global batch size: 512 | lm loss: 9.152399E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.316 | TFLOPs: 65.20 | +[default7]: iteration 131/ 3814 | consumed samples: 67072 | consumed tokens: 137363456 | elapsed time per iteration (s): 5.94 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 9.136299E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.261 | TFLOPs: 65.15 | +[default7]: iteration 132/ 3814 | consumed samples: 67584 | consumed tokens: 138412032 | elapsed time per iteration (s): 5.91 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 9.105914E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.633 | TFLOPs: 65.43 | +[default7]: iteration 133/ 3814 | consumed samples: 68096 | consumed tokens: 139460608 | elapsed time per iteration (s): 5.79 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 9.081899E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.423 | TFLOPs: 66.79 | +[default7]: iteration 134/ 3814 | consumed samples: 68608 | consumed tokens: 140509184 | elapsed time per iteration (s): 5.70 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 9.059296E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.799 | TFLOPs: 67.83 | +[default7]: iteration 135/ 3814 | consumed samples: 69120 | consumed tokens: 141557760 | elapsed time per iteration (s): 5.62 | learning rate: 1.963E-04 | global batch size: 512 | lm loss: 9.049850E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.160 | TFLOPs: 68.85 | +[default7]: iteration 136/ 3814 | consumed samples: 69632 | consumed tokens: 142606336 | elapsed time per iteration (s): 5.89 | learning rate: 1.977E-04 | global batch size: 512 | lm loss: 9.019077E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.854 | TFLOPs: 65.60 | +[default7]: iteration 137/ 3814 | consumed samples: 70144 | consumed tokens: 143654912 | elapsed time per iteration (s): 5.94 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 8.999055E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.247 | TFLOPs: 65.14 | +[default7]: iteration 138/ 3814 | consumed samples: 70656 | consumed tokens: 144703488 | elapsed time per iteration (s): 5.95 | learning rate: 2.007E-04 | global batch size: 512 | lm loss: 8.953654E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.118 | TFLOPs: 65.05 | +[default7]: iteration 139/ 3814 | consumed samples: 71168 | consumed tokens: 145752064 | elapsed time per iteration (s): 5.84 | learning rate: 2.021E-04 | global batch size: 512 | lm loss: 8.948493E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.685 | TFLOPs: 66.23 | +[default7]: iteration 140/ 3814 | consumed samples: 71680 | consumed tokens: 146800640 | elapsed time per iteration (s): 5.79 | learning rate: 2.036E-04 | global batch size: 512 | lm loss: 8.913086E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.376 | TFLOPs: 66.75 | +[default7]: iteration 141/ 3814 | consumed samples: 72192 | consumed tokens: 147849216 | elapsed time per iteration (s): 5.97 | learning rate: 2.050E-04 | global batch size: 512 | lm loss: 8.878990E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.773 | TFLOPs: 64.79 | +[default7]: iteration 142/ 3814 | consumed samples: 72704 | consumed tokens: 148897792 | elapsed time per iteration (s): 5.93 | learning rate: 2.065E-04 | global batch size: 512 | lm loss: 8.851810E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.366 | TFLOPs: 65.23 | +[default7]: iteration 143/ 3814 | consumed samples: 73216 | consumed tokens: 149946368 | elapsed time per iteration (s): 5.90 | learning rate: 2.079E-04 | global batch size: 512 | lm loss: 8.865589E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.784 | TFLOPs: 65.55 | +[default7]: iteration 144/ 3814 | consumed samples: 73728 | consumed tokens: 150994944 | elapsed time per iteration (s): 5.84 | learning rate: 2.094E-04 | global batch size: 512 | lm loss: 8.822016E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.726 | TFLOPs: 66.26 | +[default7]: iteration 145/ 3814 | consumed samples: 74240 | consumed tokens: 152043520 | elapsed time per iteration (s): 5.87 | learning rate: 2.108E-04 | global batch size: 512 | lm loss: 8.797468E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.154 | TFLOPs: 65.83 | +[default7]: iteration 146/ 3814 | consumed samples: 74752 | consumed tokens: 153092096 | elapsed time per iteration (s): 5.92 | learning rate: 2.123E-04 | global batch size: 512 | lm loss: 8.763878E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.426 | TFLOPs: 65.28 | +[default7]: iteration 147/ 3814 | consumed samples: 75264 | consumed tokens: 154140672 | elapsed time per iteration (s): 5.96 | learning rate: 2.137E-04 | global batch size: 512 | lm loss: 8.752307E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.924 | TFLOPs: 64.90 | +[default7]: iteration 148/ 3814 | consumed samples: 75776 | consumed tokens: 155189248 | elapsed time per iteration (s): 5.91 | learning rate: 2.152E-04 | global batch size: 512 | lm loss: 8.725696E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.664 | TFLOPs: 65.46 | +[default7]: iteration 149/ 3814 | consumed samples: 76288 | consumed tokens: 156237824 | elapsed time per iteration (s): 5.91 | learning rate: 2.167E-04 | global batch size: 512 | lm loss: 8.690376E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.590 | TFLOPs: 65.40 | +[default7]: iteration 150/ 3814 | consumed samples: 76800 | consumed tokens: 157286400 | elapsed time per iteration (s): 5.95 | learning rate: 2.181E-04 | global batch size: 512 | lm loss: 8.673190E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.111 | TFLOPs: 65.04 | +[default7]: iteration 151/ 3814 | consumed samples: 77312 | consumed tokens: 158334976 | elapsed time per iteration (s): 5.96 | learning rate: 2.196E-04 | global batch size: 512 | lm loss: 8.648993E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.907 | TFLOPs: 64.89 | +[default7]: iteration 152/ 3814 | consumed samples: 77824 | consumed tokens: 159383552 | elapsed time per iteration (s): 5.93 | learning rate: 2.210E-04 | global batch size: 512 | lm loss: 8.631460E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.359 | TFLOPs: 65.23 | +[default7]: iteration 153/ 3814 | consumed samples: 78336 | consumed tokens: 160432128 | elapsed time per iteration (s): 5.92 | learning rate: 2.225E-04 | global batch size: 512 | lm loss: 8.596136E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.457 | TFLOPs: 65.30 | +[default7]: iteration 154/ 3814 | consumed samples: 78848 | consumed tokens: 161480704 | elapsed time per iteration (s): 5.94 | learning rate: 2.239E-04 | global batch size: 512 | lm loss: 8.569390E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.243 | TFLOPs: 65.14 | +[default7]: iteration 155/ 3814 | consumed samples: 79360 | consumed tokens: 162529280 | elapsed time per iteration (s): 5.89 | learning rate: 2.254E-04 | global batch size: 512 | lm loss: 8.548491E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.918 | TFLOPs: 65.65 | +[default7]: iteration 156/ 3814 | consumed samples: 79872 | consumed tokens: 163577856 | elapsed time per iteration (s): 5.98 | learning rate: 2.268E-04 | global batch size: 512 | lm loss: 8.538190E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.616 | TFLOPs: 64.67 | +[default7]: iteration 157/ 3814 | consumed samples: 80384 | consumed tokens: 164626432 | elapsed time per iteration (s): 5.99 | learning rate: 2.283E-04 | global batch size: 512 | lm loss: 8.503280E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.447 | TFLOPs: 64.54 | +[default7]: iteration 158/ 3814 | consumed samples: 80896 | consumed tokens: 165675008 | elapsed time per iteration (s): 5.97 | learning rate: 2.297E-04 | global batch size: 512 | lm loss: 8.475061E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.804 | TFLOPs: 64.81 | +[default7]: iteration 159/ 3814 | consumed samples: 81408 | consumed tokens: 166723584 | elapsed time per iteration (s): 5.89 | learning rate: 2.312E-04 | global batch size: 512 | lm loss: 8.440439E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.981 | TFLOPs: 65.70 | +[default7]: iteration 160/ 3814 | consumed samples: 81920 | consumed tokens: 167772160 | elapsed time per iteration (s): 5.89 | learning rate: 2.326E-04 | global batch size: 512 | lm loss: 8.440288E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.926 | TFLOPs: 65.66 | +[default7]: iteration 161/ 3814 | consumed samples: 82432 | consumed tokens: 168820736 | elapsed time per iteration (s): 5.87 | learning rate: 2.341E-04 | global batch size: 512 | lm loss: 8.420223E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.235 | TFLOPs: 65.89 | +[default7]: iteration 162/ 3814 | consumed samples: 82944 | consumed tokens: 169869312 | elapsed time per iteration (s): 5.91 | learning rate: 2.356E-04 | global batch size: 512 | lm loss: 8.394590E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.623 | TFLOPs: 65.43 | +[default7]: iteration 163/ 3814 | consumed samples: 83456 | consumed tokens: 170917888 | elapsed time per iteration (s): 5.87 | learning rate: 2.370E-04 | global batch size: 512 | lm loss: 8.363771E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.215 | TFLOPs: 65.87 | +[default7]: iteration 164/ 3814 | consumed samples: 83968 | consumed tokens: 171966464 | elapsed time per iteration (s): 5.95 | learning rate: 2.385E-04 | global batch size: 512 | lm loss: 8.332198E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.099 | TFLOPs: 65.03 | +[default7]: iteration 165/ 3814 | consumed samples: 84480 | consumed tokens: 173015040 | elapsed time per iteration (s): 5.92 | learning rate: 2.399E-04 | global batch size: 512 | lm loss: 8.316957E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.438 | TFLOPs: 65.29 | +[default7]: iteration 166/ 3814 | consumed samples: 84992 | consumed tokens: 174063616 | elapsed time per iteration (s): 5.82 | learning rate: 2.414E-04 | global batch size: 512 | lm loss: 8.280430E+00 | loss scale: 4096.0 | grad norm: 0.040 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.917 | TFLOPs: 66.40 | +[default7]: iteration 167/ 3814 | consumed samples: 85504 | consumed tokens: 175112192 | elapsed time per iteration (s): 5.89 | learning rate: 2.428E-04 | global batch size: 512 | lm loss: 8.279720E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.920 | TFLOPs: 65.65 | +[default7]: iteration 168/ 3814 | consumed samples: 86016 | consumed tokens: 176160768 | elapsed time per iteration (s): 5.90 | learning rate: 2.443E-04 | global batch size: 512 | lm loss: 8.236567E+00 | loss scale: 4096.0 | grad norm: 0.043 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.765 | TFLOPs: 65.53 | +[default7]: iteration 169/ 3814 | consumed samples: 86528 | consumed tokens: 177209344 | elapsed time per iteration (s): 5.93 | learning rate: 2.457E-04 | global batch size: 512 | lm loss: 8.245409E+00 | loss scale: 4096.0 | grad norm: 0.046 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.292 | TFLOPs: 65.18 | +[default7]: iteration 170/ 3814 | consumed samples: 87040 | consumed tokens: 178257920 | elapsed time per iteration (s): 5.91 | learning rate: 2.472E-04 | global batch size: 512 | lm loss: 8.180381E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.629 | TFLOPs: 65.43 | +[default7]: iteration 171/ 3814 | consumed samples: 87552 | consumed tokens: 179306496 | elapsed time per iteration (s): 5.86 | learning rate: 2.486E-04 | global batch size: 512 | lm loss: 8.193555E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.345 | TFLOPs: 65.97 | +[default7]: iteration 172/ 3814 | consumed samples: 88064 | consumed tokens: 180355072 | elapsed time per iteration (s): 5.91 | learning rate: 2.501E-04 | global batch size: 512 | lm loss: 8.136150E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.564 | TFLOPs: 65.38 | +[default7]: iteration 173/ 3814 | consumed samples: 88576 | consumed tokens: 181403648 | elapsed time per iteration (s): 5.93 | learning rate: 2.515E-04 | global batch size: 512 | lm loss: 8.126885E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.335 | TFLOPs: 65.21 | +[default7]: iteration 174/ 3814 | consumed samples: 89088 | consumed tokens: 182452224 | elapsed time per iteration (s): 5.90 | learning rate: 2.530E-04 | global batch size: 512 | lm loss: 8.126040E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.733 | TFLOPs: 65.51 | +[default7]: iteration 175/ 3814 | consumed samples: 89600 | consumed tokens: 183500800 | elapsed time per iteration (s): 5.94 | learning rate: 2.545E-04 | global batch size: 512 | lm loss: 8.094327E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.153 | TFLOPs: 65.07 | +[default7]: iteration 176/ 3814 | consumed samples: 90112 | consumed tokens: 184549376 | elapsed time per iteration (s): 5.81 | learning rate: 2.559E-04 | global batch size: 512 | lm loss: 8.086197E+00 | loss scale: 4096.0 | grad norm: 0.039 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.192 | TFLOPs: 66.61 | +[default7]: iteration 177/ 3814 | consumed samples: 90624 | consumed tokens: 185597952 | elapsed time per iteration (s): 5.91 | learning rate: 2.574E-04 | global batch size: 512 | lm loss: 8.054052E+00 | loss scale: 4096.0 | grad norm: 0.037 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.614 | TFLOPs: 65.42 | +[default7]: iteration 178/ 3814 | consumed samples: 91136 | consumed tokens: 186646528 | elapsed time per iteration (s): 5.64 | learning rate: 2.588E-04 | global batch size: 512 | lm loss: 8.021345E+00 | loss scale: 4096.0 | grad norm: 0.036 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.855 | TFLOPs: 68.62 | +[default7]: iteration 179/ 3814 | consumed samples: 91648 | consumed tokens: 187695104 | elapsed time per iteration (s): 5.88 | learning rate: 2.603E-04 | global batch size: 512 | lm loss: 8.003399E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.010 | TFLOPs: 65.72 | +[default7]: iteration 180/ 3814 | consumed samples: 92160 | consumed tokens: 188743680 | elapsed time per iteration (s): 5.90 | learning rate: 2.617E-04 | global batch size: 512 | lm loss: 7.968200E+00 | loss scale: 4096.0 | grad norm: 0.050 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.813 | TFLOPs: 65.57 | +[default7]: iteration 181/ 3814 | consumed samples: 92672 | consumed tokens: 189792256 | elapsed time per iteration (s): 5.90 | learning rate: 2.632E-04 | global batch size: 512 | lm loss: 7.957362E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.744 | TFLOPs: 65.52 | +[default7]: iteration 182/ 3814 | consumed samples: 93184 | consumed tokens: 190840832 | elapsed time per iteration (s): 5.98 | learning rate: 2.646E-04 | global batch size: 512 | lm loss: 7.964464E+00 | loss scale: 4096.0 | grad norm: 0.038 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.594 | TFLOPs: 64.65 | +[default7]: iteration 183/ 3814 | consumed samples: 93696 | consumed tokens: 191889408 | elapsed time per iteration (s): 5.93 | learning rate: 2.661E-04 | global batch size: 512 | lm loss: 7.921095E+00 | loss scale: 4096.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.294 | TFLOPs: 65.18 | +[default7]: iteration 184/ 3814 | consumed samples: 94208 | consumed tokens: 192937984 | elapsed time per iteration (s): 6.02 | learning rate: 2.675E-04 | global batch size: 512 | lm loss: 7.918838E+00 | loss scale: 4096.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.089 | TFLOPs: 64.27 | +[default7]: iteration 185/ 3814 | consumed samples: 94720 | consumed tokens: 193986560 | elapsed time per iteration (s): 5.93 | learning rate: 2.690E-04 | global batch size: 512 | lm loss: 7.911599E+00 | loss scale: 4096.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.319 | TFLOPs: 65.20 | +[default7]: iteration 186/ 3814 | consumed samples: 95232 | consumed tokens: 195035136 | elapsed time per iteration (s): 5.98 | learning rate: 2.704E-04 | global batch size: 512 | lm loss: 7.891159E+00 | loss scale: 4096.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.653 | TFLOPs: 64.69 | +[default7]: iteration 187/ 3814 | consumed samples: 95744 | consumed tokens: 196083712 | elapsed time per iteration (s): 5.92 | learning rate: 2.719E-04 | global batch size: 512 | lm loss: 7.846136E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.473 | TFLOPs: 65.31 | +[default7]: iteration 188/ 3814 | consumed samples: 96256 | consumed tokens: 197132288 | elapsed time per iteration (s): 5.89 | learning rate: 2.734E-04 | global batch size: 512 | lm loss: 7.835715E+00 | loss scale: 4096.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.889 | TFLOPs: 65.63 | +[default7]: iteration 189/ 3814 | consumed samples: 96768 | consumed tokens: 198180864 | elapsed time per iteration (s): 5.94 | learning rate: 2.748E-04 | global batch size: 512 | lm loss: 7.809464E+00 | loss scale: 4096.0 | grad norm: 0.081 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.206 | TFLOPs: 65.11 | +[default7]: iteration 190/ 3814 | consumed samples: 97280 | consumed tokens: 199229440 | elapsed time per iteration (s): 5.92 | learning rate: 2.763E-04 | global batch size: 512 | lm loss: 7.813882E+00 | loss scale: 4096.0 | grad norm: 0.424 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.457 | TFLOPs: 65.30 | +[default7]: iteration 191/ 3814 | consumed samples: 97792 | consumed tokens: 200278016 | elapsed time per iteration (s): 5.93 | learning rate: 2.777E-04 | global batch size: 512 | lm loss: 7.792330E+00 | loss scale: 4096.0 | grad norm: 0.062 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.291 | TFLOPs: 65.18 | +[default7]: iteration 192/ 3814 | consumed samples: 98304 | consumed tokens: 201326592 | elapsed time per iteration (s): 5.93 | learning rate: 2.792E-04 | global batch size: 512 | lm loss: 7.778556E+00 | loss scale: 4096.0 | grad norm: 0.593 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.405 | TFLOPs: 65.26 | +[default7]: iteration 193/ 3814 | consumed samples: 98816 | consumed tokens: 202375168 | elapsed time per iteration (s): 5.85 | learning rate: 2.806E-04 | global batch size: 512 | lm loss: 7.738836E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.534 | TFLOPs: 66.12 | +[default7]: iteration 194/ 3814 | consumed samples: 99328 | consumed tokens: 203423744 | elapsed time per iteration (s): 5.83 | learning rate: 2.821E-04 | global batch size: 512 | lm loss: 7.733383E+00 | loss scale: 4096.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.862 | TFLOPs: 66.36 | +[default7]: iteration 195/ 3814 | consumed samples: 99840 | consumed tokens: 204472320 | elapsed time per iteration (s): 5.94 | learning rate: 2.835E-04 | global batch size: 512 | lm loss: 7.745108E+00 | loss scale: 4096.0 | grad norm: 0.067 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.248 | TFLOPs: 65.14 | +[default7]: iteration 196/ 3814 | consumed samples: 100352 | consumed tokens: 205520896 | elapsed time per iteration (s): 6.01 | learning rate: 2.850E-04 | global batch size: 512 | lm loss: 7.715608E+00 | loss scale: 4096.0 | grad norm: 0.075 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.130 | TFLOPs: 64.30 | +[default7]: iteration 197/ 3814 | consumed samples: 100864 | consumed tokens: 206569472 | elapsed time per iteration (s): 5.91 | learning rate: 2.864E-04 | global batch size: 512 | lm loss: 7.677945E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.630 | TFLOPs: 65.43 | +[default7]: iteration 198/ 3814 | consumed samples: 101376 | consumed tokens: 207618048 | elapsed time per iteration (s): 5.90 | learning rate: 2.879E-04 | global batch size: 512 | lm loss: 7.693727E+00 | loss scale: 4096.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.782 | TFLOPs: 65.55 | +[default7]: iteration 199/ 3814 | consumed samples: 101888 | consumed tokens: 208666624 | elapsed time per iteration (s): 5.93 | learning rate: 2.894E-04 | global batch size: 512 | lm loss: 7.665254E+00 | loss scale: 4096.0 | grad norm: 0.084 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.377 | TFLOPs: 65.24 | +[default7]: iteration 200/ 3814 | consumed samples: 102400 | consumed tokens: 209715200 | elapsed time per iteration (s): 5.85 | learning rate: 2.908E-04 | global batch size: 512 | lm loss: 7.619591E+00 | loss scale: 4096.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.586 | TFLOPs: 66.15 | +[default7]: iteration 201/ 3814 | consumed samples: 102912 | consumed tokens: 210763776 | elapsed time per iteration (s): 5.97 | learning rate: 2.923E-04 | global batch size: 512 | lm loss: 7.630900E+00 | loss scale: 4096.0 | grad norm: 0.079 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.795 | TFLOPs: 64.80 | +[default7]: iteration 202/ 3814 | consumed samples: 103424 | consumed tokens: 211812352 | elapsed time per iteration (s): 5.93 | learning rate: 2.937E-04 | global batch size: 512 | lm loss: 7.607764E+00 | loss scale: 4096.0 | grad norm: 0.081 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.382 | TFLOPs: 65.25 | +[default7]: iteration 203/ 3814 | consumed samples: 103936 | consumed tokens: 212860928 | elapsed time per iteration (s): 5.97 | learning rate: 2.952E-04 | global batch size: 512 | lm loss: 7.587873E+00 | loss scale: 4096.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.744 | TFLOPs: 64.76 | +[default7]: iteration 204/ 3814 | consumed samples: 104448 | consumed tokens: 213909504 | elapsed time per iteration (s): 5.90 | learning rate: 2.966E-04 | global batch size: 512 | lm loss: 7.566483E+00 | loss scale: 4096.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.728 | TFLOPs: 65.51 | +[default7]: iteration 205/ 3814 | consumed samples: 104960 | consumed tokens: 214958080 | elapsed time per iteration (s): 5.81 | learning rate: 2.981E-04 | global batch size: 512 | lm loss: 7.591542E+00 | loss scale: 4096.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.063 | TFLOPs: 66.51 | +[default7]: iteration 206/ 3814 | consumed samples: 105472 | consumed tokens: 216006656 | elapsed time per iteration (s): 5.89 | learning rate: 2.995E-04 | global batch size: 512 | lm loss: 7.558304E+00 | loss scale: 4096.0 | grad norm: 0.085 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.969 | TFLOPs: 65.69 | +[default7]: iteration 207/ 3814 | consumed samples: 105984 | consumed tokens: 217055232 | elapsed time per iteration (s): 5.87 | learning rate: 3.010E-04 | global batch size: 512 | lm loss: 7.514569E+00 | loss scale: 4096.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.156 | TFLOPs: 65.83 | +[default7]: iteration 208/ 3814 | consumed samples: 106496 | consumed tokens: 218103808 | elapsed time per iteration (s): 5.89 | learning rate: 3.024E-04 | global batch size: 512 | lm loss: 7.511181E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.861 | TFLOPs: 65.61 | +[default7]: iteration 209/ 3814 | consumed samples: 107008 | consumed tokens: 219152384 | elapsed time per iteration (s): 5.90 | learning rate: 3.039E-04 | global batch size: 512 | lm loss: 7.505405E+00 | loss scale: 4096.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.781 | TFLOPs: 65.55 | +[default7]: iteration 210/ 3814 | consumed samples: 107520 | consumed tokens: 220200960 | elapsed time per iteration (s): 5.89 | learning rate: 3.053E-04 | global batch size: 512 | lm loss: 7.495893E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.876 | TFLOPs: 65.62 | +[default7]: iteration 211/ 3814 | consumed samples: 108032 | consumed tokens: 221249536 | elapsed time per iteration (s): 5.93 | learning rate: 3.068E-04 | global batch size: 512 | lm loss: 7.444227E+00 | loss scale: 4096.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.286 | TFLOPs: 65.17 | +[default7]: iteration 212/ 3814 | consumed samples: 108544 | consumed tokens: 222298112 | elapsed time per iteration (s): 5.90 | learning rate: 3.083E-04 | global batch size: 512 | lm loss: 7.481379E+00 | loss scale: 4096.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.811 | TFLOPs: 65.57 | +[default7]: iteration 213/ 3814 | consumed samples: 109056 | consumed tokens: 223346688 | elapsed time per iteration (s): 5.97 | learning rate: 3.097E-04 | global batch size: 512 | lm loss: 7.440928E+00 | loss scale: 4096.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.802 | TFLOPs: 64.81 | +[default7]: iteration 214/ 3814 | consumed samples: 109568 | consumed tokens: 224395264 | elapsed time per iteration (s): 5.88 | learning rate: 3.112E-04 | global batch size: 512 | lm loss: 7.417747E+00 | loss scale: 4096.0 | grad norm: 0.041 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.125 | TFLOPs: 65.81 | +[default7]: iteration 215/ 3814 | consumed samples: 110080 | consumed tokens: 225443840 | elapsed time per iteration (s): 5.83 | learning rate: 3.126E-04 | global batch size: 512 | lm loss: 7.430084E+00 | loss scale: 4096.0 | grad norm: 0.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.764 | TFLOPs: 66.29 | +[default7]: iteration 216/ 3814 | consumed samples: 110592 | consumed tokens: 226492416 | elapsed time per iteration (s): 5.94 | learning rate: 3.141E-04 | global batch size: 512 | lm loss: 7.434466E+00 | loss scale: 4096.0 | grad norm: 0.082 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.173 | TFLOPs: 65.09 | +[default7]: iteration 217/ 3814 | consumed samples: 111104 | consumed tokens: 227540992 | elapsed time per iteration (s): 5.92 | learning rate: 3.155E-04 | global batch size: 512 | lm loss: 7.398223E+00 | loss scale: 4096.0 | grad norm: 0.051 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.422 | TFLOPs: 65.28 | +[default7]: iteration 218/ 3814 | consumed samples: 111616 | consumed tokens: 228589568 | elapsed time per iteration (s): 5.98 | learning rate: 3.170E-04 | global batch size: 512 | lm loss: 7.379918E+00 | loss scale: 4096.0 | grad norm: 0.079 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.591 | TFLOPs: 64.65 | +[default7]: iteration 219/ 3814 | consumed samples: 112128 | consumed tokens: 229638144 | elapsed time per iteration (s): 5.90 | learning rate: 3.184E-04 | global batch size: 512 | lm loss: 7.366367E+00 | loss scale: 4096.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.744 | TFLOPs: 65.52 | +[default7]: iteration 220/ 3814 | consumed samples: 112640 | consumed tokens: 230686720 | elapsed time per iteration (s): 5.95 | learning rate: 3.199E-04 | global batch size: 512 | lm loss: 7.355317E+00 | loss scale: 4096.0 | grad norm: 0.076 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.049 | TFLOPs: 64.99 | +[default7]: iteration 221/ 3814 | consumed samples: 113152 | consumed tokens: 231735296 | elapsed time per iteration (s): 5.87 | learning rate: 3.213E-04 | global batch size: 512 | lm loss: 7.390779E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.178 | TFLOPs: 65.85 | +[default7]: iteration 222/ 3814 | consumed samples: 113664 | consumed tokens: 232783872 | elapsed time per iteration (s): 5.88 | learning rate: 3.228E-04 | global batch size: 512 | lm loss: 7.359792E+00 | loss scale: 4096.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.015 | TFLOPs: 65.72 | +[default7]: iteration 223/ 3814 | consumed samples: 114176 | consumed tokens: 233832448 | elapsed time per iteration (s): 6.00 | learning rate: 3.242E-04 | global batch size: 512 | lm loss: 7.328635E+00 | loss scale: 4096.0 | grad norm: 0.056 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.321 | TFLOPs: 64.44 | +[default7]: iteration 224/ 3814 | consumed samples: 114688 | consumed tokens: 234881024 | elapsed time per iteration (s): 5.89 | learning rate: 3.257E-04 | global batch size: 512 | lm loss: 7.341724E+00 | loss scale: 4096.0 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.948 | TFLOPs: 65.67 | +[default7]: iteration 225/ 3814 | consumed samples: 115200 | consumed tokens: 235929600 | elapsed time per iteration (s): 5.98 | learning rate: 3.272E-04 | global batch size: 512 | lm loss: 7.337786E+00 | loss scale: 4096.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.584 | TFLOPs: 64.64 | +[default7]: iteration 226/ 3814 | consumed samples: 115712 | consumed tokens: 236978176 | elapsed time per iteration (s): 5.87 | learning rate: 3.286E-04 | global batch size: 512 | lm loss: 7.340064E+00 | loss scale: 4096.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.188 | TFLOPs: 65.85 | +[default7]: iteration 227/ 3814 | consumed samples: 116224 | consumed tokens: 238026752 | elapsed time per iteration (s): 5.92 | learning rate: 3.301E-04 | global batch size: 512 | lm loss: 7.291409E+00 | loss scale: 4096.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.528 | TFLOPs: 65.36 | +[default7]: iteration 228/ 3814 | consumed samples: 116736 | consumed tokens: 239075328 | elapsed time per iteration (s): 5.92 | learning rate: 3.315E-04 | global batch size: 512 | lm loss: 7.299720E+00 | loss scale: 4096.0 | grad norm: 0.300 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.470 | TFLOPs: 65.31 | +[default7]: iteration 229/ 3814 | consumed samples: 117248 | consumed tokens: 240123904 | elapsed time per iteration (s): 5.94 | learning rate: 3.330E-04 | global batch size: 512 | lm loss: 7.271026E+00 | loss scale: 4096.0 | grad norm: 0.085 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.193 | TFLOPs: 65.10 | +[default7]: iteration 230/ 3814 | consumed samples: 117760 | consumed tokens: 241172480 | elapsed time per iteration (s): 5.65 | learning rate: 3.344E-04 | global batch size: 512 | lm loss: 7.254303E+00 | loss scale: 4096.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.654 | TFLOPs: 68.47 | +[default7]: iteration 231/ 3814 | consumed samples: 118272 | consumed tokens: 242221056 | elapsed time per iteration (s): 5.88 | learning rate: 3.359E-04 | global batch size: 512 | lm loss: 7.244864E+00 | loss scale: 4096.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.046 | TFLOPs: 65.75 | +[default7]: iteration 232/ 3814 | consumed samples: 118784 | consumed tokens: 243269632 | elapsed time per iteration (s): 5.96 | learning rate: 3.373E-04 | global batch size: 512 | lm loss: 7.240613E+00 | loss scale: 4096.0 | grad norm: 0.096 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.913 | TFLOPs: 64.89 | +[default7]: iteration 233/ 3814 | consumed samples: 119296 | consumed tokens: 244318208 | elapsed time per iteration (s): 5.93 | learning rate: 3.388E-04 | global batch size: 512 | lm loss: 7.223609E+00 | loss scale: 4096.0 | grad norm: 0.093 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.390 | TFLOPs: 65.25 | +[default7]: iteration 234/ 3814 | consumed samples: 119808 | consumed tokens: 245366784 | elapsed time per iteration (s): 5.91 | learning rate: 3.402E-04 | global batch size: 512 | lm loss: 7.191864E+00 | loss scale: 4096.0 | grad norm: 0.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.606 | TFLOPs: 65.41 | +[default7]: iteration 235/ 3814 | consumed samples: 120320 | consumed tokens: 246415360 | elapsed time per iteration (s): 5.96 | learning rate: 3.417E-04 | global batch size: 512 | lm loss: 7.213235E+00 | loss scale: 4096.0 | grad norm: 0.092 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.878 | TFLOPs: 64.86 | +[default7]: iteration 236/ 3814 | consumed samples: 120832 | consumed tokens: 247463936 | elapsed time per iteration (s): 5.94 | learning rate: 3.432E-04 | global batch size: 512 | lm loss: 7.183730E+00 | loss scale: 4096.0 | grad norm: 0.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.191 | TFLOPs: 65.10 | +[default7]: iteration 237/ 3814 | consumed samples: 121344 | consumed tokens: 248512512 | elapsed time per iteration (s): 5.93 | learning rate: 3.446E-04 | global batch size: 512 | lm loss: 7.193408E+00 | loss scale: 4096.0 | grad norm: 0.072 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.315 | TFLOPs: 65.19 | +[default7]: iteration 238/ 3814 | consumed samples: 121856 | consumed tokens: 249561088 | elapsed time per iteration (s): 5.94 | learning rate: 3.461E-04 | global batch size: 512 | lm loss: 7.166681E+00 | loss scale: 4096.0 | grad norm: 0.086 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.242 | TFLOPs: 65.14 | +[default7]: iteration 239/ 3814 | consumed samples: 122368 | consumed tokens: 250609664 | elapsed time per iteration (s): 5.95 | learning rate: 3.475E-04 | global batch size: 512 | lm loss: 7.150960E+00 | loss scale: 4096.0 | grad norm: 0.042 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.041 | TFLOPs: 64.99 | +[default7]: iteration 240/ 3814 | consumed samples: 122880 | consumed tokens: 251658240 | elapsed time per iteration (s): 5.90 | learning rate: 3.490E-04 | global batch size: 512 | lm loss: 7.156374E+00 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.716 | TFLOPs: 65.50 | +[default7]: iteration 241/ 3814 | consumed samples: 123392 | consumed tokens: 252706816 | elapsed time per iteration (s): 5.99 | learning rate: 3.504E-04 | global batch size: 512 | lm loss: 7.143648E+00 | loss scale: 4096.0 | grad norm: 0.055 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.482 | TFLOPs: 64.57 | +[default7]: iteration 242/ 3814 | consumed samples: 123904 | consumed tokens: 253755392 | elapsed time per iteration (s): 6.01 | learning rate: 3.519E-04 | global batch size: 512 | lm loss: 7.141851E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.187 | TFLOPs: 64.34 | +[default7]: iteration 243/ 3814 | consumed samples: 124416 | consumed tokens: 254803968 | elapsed time per iteration (s): 5.97 | learning rate: 3.533E-04 | global batch size: 512 | lm loss: 7.090278E+00 | loss scale: 4096.0 | grad norm: 0.050 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.713 | TFLOPs: 64.74 | +[default7]: iteration 244/ 3814 | consumed samples: 124928 | consumed tokens: 255852544 | elapsed time per iteration (s): 6.01 | learning rate: 3.548E-04 | global batch size: 512 | lm loss: 7.119850E+00 | loss scale: 4096.0 | grad norm: 0.066 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.181 | TFLOPs: 64.34 | +[default7]: iteration 245/ 3814 | consumed samples: 125440 | consumed tokens: 256901120 | elapsed time per iteration (s): 5.88 | learning rate: 3.562E-04 | global batch size: 512 | lm loss: 7.102881E+00 | loss scale: 4096.0 | grad norm: 0.060 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.003 | TFLOPs: 65.71 | +[default7]: iteration 246/ 3814 | consumed samples: 125952 | consumed tokens: 257949696 | elapsed time per iteration (s): 5.65 | learning rate: 3.577E-04 | global batch size: 512 | lm loss: 7.100522E+00 | loss scale: 4096.0 | grad norm: 0.053 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.626 | TFLOPs: 68.45 | +[default7]: iteration 247/ 3814 | consumed samples: 126464 | consumed tokens: 258998272 | elapsed time per iteration (s): 5.92 | learning rate: 3.591E-04 | global batch size: 512 | lm loss: 7.051473E+00 | loss scale: 4096.0 | grad norm: 0.052 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.446 | TFLOPs: 65.29 | +[default7]: iteration 248/ 3814 | consumed samples: 126976 | consumed tokens: 260046848 | elapsed time per iteration (s): 5.89 | learning rate: 3.606E-04 | global batch size: 512 | lm loss: 7.052402E+00 | loss scale: 4096.0 | grad norm: 0.091 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.930 | TFLOPs: 65.66 | +[default7]: iteration 249/ 3814 | consumed samples: 127488 | consumed tokens: 261095424 | elapsed time per iteration (s): 5.90 | learning rate: 3.621E-04 | global batch size: 512 | lm loss: 7.073118E+00 | loss scale: 4096.0 | grad norm: 0.080 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.741 | TFLOPs: 65.52 | +[default7]: iteration 250/ 3814 | consumed samples: 128000 | consumed tokens: 262144000 | elapsed time per iteration (s): 5.97 | learning rate: 3.635E-04 | global batch size: 512 | lm loss: 7.042840E+00 | loss scale: 4096.0 | grad norm: 0.060 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.759 | TFLOPs: 64.77 | +[default0]:saving checkpoint at iteration 250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 07:57:33,983] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step250 is begin to save! +[default1]:[2023-02-16 07:57:34,012] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,012] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,203] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,204] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:34,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,199] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,334] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,305] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:34,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,382] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,390] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:34,446] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,438] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:34,559] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,495] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:34,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,561] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:34,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,621] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,740] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,699] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,700] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:34,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,809] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,809] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:34,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,815] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:34,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,872] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:34,946] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:34,947] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:34,947] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:34,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,021] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,022] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,021] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,101] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,101] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:35,162] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,162] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,210] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,264] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,265] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,217] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:35,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,273] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,319] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,374] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,330] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:35,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,386] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,509] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,510] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,574] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,697] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,753] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,699] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:35,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,758] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,807] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,808] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,862] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,862] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,814] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:35,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:35,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,919] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:35,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:35,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:35,942] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:35,942] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:36,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:36,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:36,008] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,009] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:36,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,070] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:36,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:36,089] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:36,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:36,143] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 07:57:36,137] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,137] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 07:57:36,199] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:36,200] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 07:57:36,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 07:57:36,202] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_01_model_states.pt +[default1]:[2023-02-16 07:57:36,202] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 07:57:36,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 07:57:36,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,197] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:36,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,269] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:36,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,326] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:36,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 07:57:36,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 07:57:36,385] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_00_model_states.pt +[default0]:[2023-02-16 07:57:36,385] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 07:57:36,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/mp_rank_00_model_states.pt. +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 07:57:36,415] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 07:57:36,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:36,899] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:36,899] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:36,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:36,943] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:36,943] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:36,919] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:36,920] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:36,920] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:36,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:36,988] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:36,988] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,029] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,038] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,055] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,055] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,083] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,083] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,018] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,029] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,029] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,029] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,099] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,041] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,041] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,041] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,052] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,052] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,052] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,054] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,054] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,054] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,094] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,094] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,094] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,078] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,078] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,078] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,099] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,099] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,084] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,084] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,092] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,092] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,156] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,158] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,080] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,080] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,081] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,142] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,142] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,131] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,131] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,140] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,143] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,143] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,143] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,170] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,170] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,139] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,139] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,128] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,140] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,140] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,158] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,166] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,166] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,194] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,194] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,194] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,149] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,150] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,150] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,135] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,135] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,135] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,141] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,141] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,198] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,218] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,164] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,165] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,167] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,167] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,167] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,173] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,173] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,173] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,250] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,250] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,224] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,224] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,224] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,260] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,231] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,180] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,180] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,180] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default1]:[2023-02-16 07:57:37,243] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 07:57:37,243] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 07:57:37,243] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,241] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,241] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,223] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,254] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,267] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,212] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,208] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,208] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,209] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,206] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,206] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,259] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,259] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default2]:[2023-02-16 07:57:37,255] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 07:57:37,255] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 07:57:37,255] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default3]:[2023-02-16 07:57:37,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 07:57:37,291] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 07:57:37,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default5]:[2023-02-16 07:57:37,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 07:57:37,291] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 07:57:37,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,315] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,315] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,315] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default0]:[2023-02-16 07:57:37,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 07:57:37,274] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 07:57:37,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,302] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,302] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,302] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:[2023-02-16 07:57:37,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 07:57:37,339] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 07:57:37,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,392] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default4]:[2023-02-16 07:57:37,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 07:57:37,379] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 07:57:37,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default6]:[2023-02-16 07:57:37,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 07:57:37,423] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step250/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 07:57:37,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step250 is ready now! +[default7]:time (ms) | save-checkpoint: 3573.31 +[default0]: successfully saved checkpoint at iteration 250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]: iteration 251/ 3814 | consumed samples: 128512 | consumed tokens: 263192576 | elapsed time per iteration (s): 9.56 | learning rate: 3.650E-04 | global batch size: 512 | lm loss: 7.028556E+00 | loss scale: 4096.0 | grad norm: 0.053 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 53.529 | TFLOPs: 40.43 | +[default7]: iteration 252/ 3814 | consumed samples: 129024 | consumed tokens: 264241152 | elapsed time per iteration (s): 5.86 | learning rate: 3.664E-04 | global batch size: 512 | lm loss: 7.018734E+00 | loss scale: 4096.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.385 | TFLOPs: 66.00 | +[default7]: iteration 253/ 3814 | consumed samples: 129536 | consumed tokens: 265289728 | elapsed time per iteration (s): 5.93 | learning rate: 3.679E-04 | global batch size: 512 | lm loss: 7.019761E+00 | loss scale: 4096.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.370 | TFLOPs: 65.24 | +[default7]: iteration 254/ 3814 | consumed samples: 130048 | consumed tokens: 266338304 | elapsed time per iteration (s): 5.93 | learning rate: 3.693E-04 | global batch size: 512 | lm loss: 6.978835E+00 | loss scale: 4096.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.309 | TFLOPs: 65.19 | +[default7]: iteration 255/ 3814 | consumed samples: 130560 | consumed tokens: 267386880 | elapsed time per iteration (s): 5.95 | learning rate: 3.708E-04 | global batch size: 512 | lm loss: 7.006974E+00 | loss scale: 4096.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.120 | TFLOPs: 65.05 | +[default7]: iteration 256/ 3814 | consumed samples: 131072 | consumed tokens: 268435456 | elapsed time per iteration (s): 5.95 | learning rate: 3.722E-04 | global batch size: 512 | lm loss: 6.989872E+00 | loss scale: 4096.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.030 | TFLOPs: 64.98 | +[default7]: iteration 257/ 3814 | consumed samples: 131584 | consumed tokens: 269484032 | elapsed time per iteration (s): 5.86 | learning rate: 3.737E-04 | global batch size: 512 | lm loss: 6.982117E+00 | loss scale: 4096.0 | grad norm: 0.089 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.401 | TFLOPs: 66.01 | +[default7]: iteration 258/ 3814 | consumed samples: 132096 | consumed tokens: 270532608 | elapsed time per iteration (s): 5.89 | learning rate: 3.751E-04 | global batch size: 512 | lm loss: 6.970227E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.894 | TFLOPs: 65.63 | +[default7]: iteration 259/ 3814 | consumed samples: 132608 | consumed tokens: 271581184 | elapsed time per iteration (s): 5.87 | learning rate: 3.766E-04 | global batch size: 512 | lm loss: 6.929323E+00 | loss scale: 4096.0 | grad norm: 0.080 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.220 | TFLOPs: 65.88 | +[default7]: iteration 260/ 3814 | consumed samples: 133120 | consumed tokens: 272629760 | elapsed time per iteration (s): 5.97 | learning rate: 3.780E-04 | global batch size: 512 | lm loss: 6.926101E+00 | loss scale: 4096.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.802 | TFLOPs: 64.81 | +[default7]: iteration 261/ 3814 | consumed samples: 133632 | consumed tokens: 273678336 | elapsed time per iteration (s): 5.96 | learning rate: 3.795E-04 | global batch size: 512 | lm loss: 6.926495E+00 | loss scale: 4096.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.901 | TFLOPs: 64.88 | +[default7]: iteration 262/ 3814 | consumed samples: 134144 | consumed tokens: 274726912 | elapsed time per iteration (s): 5.97 | learning rate: 3.810E-04 | global batch size: 512 | lm loss: 6.905708E+00 | loss scale: 4096.0 | grad norm: 0.095 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.776 | TFLOPs: 64.79 | +[default7]: iteration 263/ 3814 | consumed samples: 134656 | consumed tokens: 275775488 | elapsed time per iteration (s): 5.94 | learning rate: 3.824E-04 | global batch size: 512 | lm loss: 6.894135E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.260 | TFLOPs: 65.15 | +[default7]: iteration 264/ 3814 | consumed samples: 135168 | consumed tokens: 276824064 | elapsed time per iteration (s): 5.92 | learning rate: 3.839E-04 | global batch size: 512 | lm loss: 6.854008E+00 | loss scale: 4096.0 | grad norm: 0.078 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.452 | TFLOPs: 65.30 | +[default7]: iteration 265/ 3814 | consumed samples: 135680 | consumed tokens: 277872640 | elapsed time per iteration (s): 5.94 | learning rate: 3.853E-04 | global batch size: 512 | lm loss: 6.899553E+00 | loss scale: 4096.0 | grad norm: 0.071 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.155 | TFLOPs: 65.07 | +[default7]: iteration 266/ 3814 | consumed samples: 136192 | consumed tokens: 278921216 | elapsed time per iteration (s): 5.84 | learning rate: 3.868E-04 | global batch size: 512 | lm loss: 6.889482E+00 | loss scale: 4096.0 | grad norm: 0.073 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.735 | TFLOPs: 66.27 | +[default7]: iteration 267/ 3814 | consumed samples: 136704 | consumed tokens: 279969792 | elapsed time per iteration (s): 5.89 | learning rate: 3.882E-04 | global batch size: 512 | lm loss: 6.860197E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.919 | TFLOPs: 65.65 | +[default7]: iteration 268/ 3814 | consumed samples: 137216 | consumed tokens: 281018368 | elapsed time per iteration (s): 5.99 | learning rate: 3.897E-04 | global batch size: 512 | lm loss: 6.871693E+00 | loss scale: 4096.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.480 | TFLOPs: 64.56 | +[default7]: iteration 269/ 3814 | consumed samples: 137728 | consumed tokens: 282066944 | elapsed time per iteration (s): 5.94 | learning rate: 3.911E-04 | global batch size: 512 | lm loss: 6.857836E+00 | loss scale: 4096.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.163 | TFLOPs: 65.08 | +[default7]: iteration 270/ 3814 | consumed samples: 138240 | consumed tokens: 283115520 | elapsed time per iteration (s): 5.84 | learning rate: 3.926E-04 | global batch size: 512 | lm loss: 6.816959E+00 | loss scale: 4096.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.651 | TFLOPs: 66.20 | +[default7]: iteration 271/ 3814 | consumed samples: 138752 | consumed tokens: 284164096 | elapsed time per iteration (s): 5.90 | learning rate: 3.940E-04 | global batch size: 512 | lm loss: 6.838911E+00 | loss scale: 4096.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.718 | TFLOPs: 65.50 | +[default7]: iteration 272/ 3814 | consumed samples: 139264 | consumed tokens: 285212672 | elapsed time per iteration (s): 5.92 | learning rate: 3.955E-04 | global batch size: 512 | lm loss: 6.817267E+00 | loss scale: 4096.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.555 | TFLOPs: 65.38 | +[default7]: iteration 273/ 3814 | consumed samples: 139776 | consumed tokens: 286261248 | elapsed time per iteration (s): 5.92 | learning rate: 3.969E-04 | global batch size: 512 | lm loss: 6.775578E+00 | loss scale: 4096.0 | grad norm: 0.088 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.534 | TFLOPs: 65.36 | +[default7]: iteration 274/ 3814 | consumed samples: 140288 | consumed tokens: 287309824 | elapsed time per iteration (s): 5.97 | learning rate: 3.984E-04 | global batch size: 512 | lm loss: 6.810627E+00 | loss scale: 4096.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.814 | TFLOPs: 64.82 | +[default7]: iteration 275/ 3814 | consumed samples: 140800 | consumed tokens: 288358400 | elapsed time per iteration (s): 5.87 | learning rate: 3.999E-04 | global batch size: 512 | lm loss: 6.774964E+00 | loss scale: 4096.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.156 | TFLOPs: 65.83 | +[default7]: iteration 276/ 3814 | consumed samples: 141312 | consumed tokens: 289406976 | elapsed time per iteration (s): 5.88 | learning rate: 4.013E-04 | global batch size: 512 | lm loss: 6.747009E+00 | loss scale: 4096.0 | grad norm: 0.077 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.117 | TFLOPs: 65.80 | +[default7]: iteration 277/ 3814 | consumed samples: 141824 | consumed tokens: 290455552 | elapsed time per iteration (s): 5.96 | learning rate: 4.028E-04 | global batch size: 512 | lm loss: 6.739010E+00 | loss scale: 4096.0 | grad norm: 0.103 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.959 | TFLOPs: 64.93 | +[default7]: iteration 278/ 3814 | consumed samples: 142336 | consumed tokens: 291504128 | elapsed time per iteration (s): 5.98 | learning rate: 4.042E-04 | global batch size: 512 | lm loss: 6.744470E+00 | loss scale: 4096.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.561 | TFLOPs: 64.63 | +[default7]: iteration 279/ 3814 | consumed samples: 142848 | consumed tokens: 292552704 | elapsed time per iteration (s): 5.96 | learning rate: 4.057E-04 | global batch size: 512 | lm loss: 6.748622E+00 | loss scale: 4096.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.887 | TFLOPs: 64.87 | +[default7]: iteration 280/ 3814 | consumed samples: 143360 | consumed tokens: 293601280 | elapsed time per iteration (s): 5.97 | learning rate: 4.071E-04 | global batch size: 512 | lm loss: 6.729491E+00 | loss scale: 4096.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.736 | TFLOPs: 64.76 | +[default7]: iteration 281/ 3814 | consumed samples: 143872 | consumed tokens: 294649856 | elapsed time per iteration (s): 6.01 | learning rate: 4.086E-04 | global batch size: 512 | lm loss: 6.769601E+00 | loss scale: 4096.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.235 | TFLOPs: 64.38 | +[default7]: iteration 282/ 3814 | consumed samples: 144384 | consumed tokens: 295698432 | elapsed time per iteration (s): 6.00 | learning rate: 4.100E-04 | global batch size: 512 | lm loss: 6.712327E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.273 | TFLOPs: 64.41 | +[default7]: iteration 283/ 3814 | consumed samples: 144896 | consumed tokens: 296747008 | elapsed time per iteration (s): 6.00 | learning rate: 4.115E-04 | global batch size: 512 | lm loss: 6.723920E+00 | loss scale: 4096.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.306 | TFLOPs: 64.43 | +[default7]: iteration 284/ 3814 | consumed samples: 145408 | consumed tokens: 297795584 | elapsed time per iteration (s): 5.93 | learning rate: 4.129E-04 | global batch size: 512 | lm loss: 6.685861E+00 | loss scale: 4096.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.366 | TFLOPs: 65.23 | +[default7]: iteration 285/ 3814 | consumed samples: 145920 | consumed tokens: 298844160 | elapsed time per iteration (s): 5.92 | learning rate: 4.144E-04 | global batch size: 512 | lm loss: 6.698463E+00 | loss scale: 4096.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.529 | TFLOPs: 65.36 | +[default7]: iteration 286/ 3814 | consumed samples: 146432 | consumed tokens: 299892736 | elapsed time per iteration (s): 6.03 | learning rate: 4.159E-04 | global batch size: 512 | lm loss: 6.664089E+00 | loss scale: 4096.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.950 | TFLOPs: 64.16 | +[default7]: iteration 287/ 3814 | consumed samples: 146944 | consumed tokens: 300941312 | elapsed time per iteration (s): 6.03 | learning rate: 4.173E-04 | global batch size: 512 | lm loss: 6.653544E+00 | loss scale: 4096.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.935 | TFLOPs: 64.15 | +[default7]: iteration 288/ 3814 | consumed samples: 147456 | consumed tokens: 301989888 | elapsed time per iteration (s): 5.99 | learning rate: 4.188E-04 | global batch size: 512 | lm loss: 6.658150E+00 | loss scale: 4096.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.537 | TFLOPs: 64.61 | +[default7]: iteration 289/ 3814 | consumed samples: 147968 | consumed tokens: 303038464 | elapsed time per iteration (s): 5.96 | learning rate: 4.202E-04 | global batch size: 512 | lm loss: 6.643257E+00 | loss scale: 4096.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.920 | TFLOPs: 64.90 | +[default7]: iteration 290/ 3814 | consumed samples: 148480 | consumed tokens: 304087040 | elapsed time per iteration (s): 6.01 | learning rate: 4.217E-04 | global batch size: 512 | lm loss: 6.630081E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.182 | TFLOPs: 64.34 | +[default7]: iteration 291/ 3814 | consumed samples: 148992 | consumed tokens: 305135616 | elapsed time per iteration (s): 6.01 | learning rate: 4.231E-04 | global batch size: 512 | lm loss: 6.624084E+00 | loss scale: 4096.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.132 | TFLOPs: 64.30 | +[default7]: iteration 292/ 3814 | consumed samples: 149504 | consumed tokens: 306184192 | elapsed time per iteration (s): 6.02 | learning rate: 4.246E-04 | global batch size: 512 | lm loss: 6.638290E+00 | loss scale: 4096.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.007 | TFLOPs: 64.21 | +[default7]: iteration 293/ 3814 | consumed samples: 150016 | consumed tokens: 307232768 | elapsed time per iteration (s): 6.03 | learning rate: 4.260E-04 | global batch size: 512 | lm loss: 6.592233E+00 | loss scale: 4096.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.962 | TFLOPs: 64.17 | +[default7]: iteration 294/ 3814 | consumed samples: 150528 | consumed tokens: 308281344 | elapsed time per iteration (s): 5.99 | learning rate: 4.275E-04 | global batch size: 512 | lm loss: 6.566069E+00 | loss scale: 4096.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.472 | TFLOPs: 64.56 | +[default7]: iteration 295/ 3814 | consumed samples: 151040 | consumed tokens: 309329920 | elapsed time per iteration (s): 5.97 | learning rate: 4.289E-04 | global batch size: 512 | lm loss: 6.583546E+00 | loss scale: 4096.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.751 | TFLOPs: 64.77 | +[default7]: iteration 296/ 3814 | consumed samples: 151552 | consumed tokens: 310378496 | elapsed time per iteration (s): 6.00 | learning rate: 4.304E-04 | global batch size: 512 | lm loss: 6.561430E+00 | loss scale: 4096.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.330 | TFLOPs: 64.45 | +[default7]: iteration 297/ 3814 | consumed samples: 152064 | consumed tokens: 311427072 | elapsed time per iteration (s): 5.99 | learning rate: 4.318E-04 | global batch size: 512 | lm loss: 6.594349E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.508 | TFLOPs: 64.59 | +[default7]: iteration 298/ 3814 | consumed samples: 152576 | consumed tokens: 312475648 | elapsed time per iteration (s): 5.98 | learning rate: 4.333E-04 | global batch size: 512 | lm loss: 6.621038E+00 | loss scale: 4096.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.565 | TFLOPs: 64.63 | +[default7]: iteration 299/ 3814 | consumed samples: 153088 | consumed tokens: 313524224 | elapsed time per iteration (s): 5.90 | learning rate: 4.348E-04 | global batch size: 512 | lm loss: 6.582146E+00 | loss scale: 4096.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.843 | TFLOPs: 65.59 | +[default7]: iteration 300/ 3814 | consumed samples: 153600 | consumed tokens: 314572800 | elapsed time per iteration (s): 6.00 | learning rate: 4.362E-04 | global batch size: 512 | lm loss: 6.586152E+00 | loss scale: 4096.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.389 | TFLOPs: 64.50 | +[default7]: iteration 301/ 3814 | consumed samples: 154112 | consumed tokens: 315621376 | elapsed time per iteration (s): 5.98 | learning rate: 4.377E-04 | global batch size: 512 | lm loss: 6.567501E+00 | loss scale: 4096.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.566 | TFLOPs: 64.63 | +[default7]: iteration 302/ 3814 | consumed samples: 154624 | consumed tokens: 316669952 | elapsed time per iteration (s): 6.01 | learning rate: 4.391E-04 | global batch size: 512 | lm loss: 6.548504E+00 | loss scale: 4096.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.242 | TFLOPs: 64.38 | +[default7]: iteration 303/ 3814 | consumed samples: 155136 | consumed tokens: 317718528 | elapsed time per iteration (s): 5.99 | learning rate: 4.406E-04 | global batch size: 512 | lm loss: 6.535009E+00 | loss scale: 4096.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.512 | TFLOPs: 64.59 | +[default7]: iteration 304/ 3814 | consumed samples: 155648 | consumed tokens: 318767104 | elapsed time per iteration (s): 5.98 | learning rate: 4.420E-04 | global batch size: 512 | lm loss: 6.559772E+00 | loss scale: 4096.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 305/ 3814 | consumed samples: 156160 | consumed tokens: 319815680 | elapsed time per iteration (s): 5.98 | learning rate: 4.435E-04 | global batch size: 512 | lm loss: 6.515721E+00 | loss scale: 4096.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.582 | TFLOPs: 64.64 | +[default7]: iteration 306/ 3814 | consumed samples: 156672 | consumed tokens: 320864256 | elapsed time per iteration (s): 6.01 | learning rate: 4.449E-04 | global batch size: 512 | lm loss: 6.500849E+00 | loss scale: 4096.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.252 | TFLOPs: 64.39 | +[default7]: iteration 307/ 3814 | consumed samples: 157184 | consumed tokens: 321912832 | elapsed time per iteration (s): 5.98 | learning rate: 4.464E-04 | global batch size: 512 | lm loss: 6.505146E+00 | loss scale: 4096.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.620 | TFLOPs: 64.67 | +[default7]: iteration 308/ 3814 | consumed samples: 157696 | consumed tokens: 322961408 | elapsed time per iteration (s): 6.00 | learning rate: 4.478E-04 | global batch size: 512 | lm loss: 6.502836E+00 | loss scale: 4096.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.344 | TFLOPs: 64.46 | +[default7]: iteration 309/ 3814 | consumed samples: 158208 | consumed tokens: 324009984 | elapsed time per iteration (s): 5.95 | learning rate: 4.493E-04 | global batch size: 512 | lm loss: 6.491033E+00 | loss scale: 4096.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.111 | TFLOPs: 65.04 | +[default7]: iteration 310/ 3814 | consumed samples: 158720 | consumed tokens: 325058560 | elapsed time per iteration (s): 6.05 | learning rate: 4.507E-04 | global batch size: 512 | lm loss: 6.476629E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.689 | TFLOPs: 63.97 | +[default7]: iteration 311/ 3814 | consumed samples: 159232 | consumed tokens: 326107136 | elapsed time per iteration (s): 5.96 | learning rate: 4.522E-04 | global batch size: 512 | lm loss: 6.483226E+00 | loss scale: 4096.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.882 | TFLOPs: 64.87 | +[default7]: iteration 312/ 3814 | consumed samples: 159744 | consumed tokens: 327155712 | elapsed time per iteration (s): 5.99 | learning rate: 4.537E-04 | global batch size: 512 | lm loss: 6.483469E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.525 | TFLOPs: 64.60 | +[default7]: iteration 313/ 3814 | consumed samples: 160256 | consumed tokens: 328204288 | elapsed time per iteration (s): 5.93 | learning rate: 4.551E-04 | global batch size: 512 | lm loss: 6.466271E+00 | loss scale: 4096.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.411 | TFLOPs: 65.27 | +[default7]: iteration 314/ 3814 | consumed samples: 160768 | consumed tokens: 329252864 | elapsed time per iteration (s): 5.98 | learning rate: 4.566E-04 | global batch size: 512 | lm loss: 6.457303E+00 | loss scale: 4096.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 315/ 3814 | consumed samples: 161280 | consumed tokens: 330301440 | elapsed time per iteration (s): 5.99 | learning rate: 4.580E-04 | global batch size: 512 | lm loss: 6.450376E+00 | loss scale: 4096.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.422 | TFLOPs: 64.52 | +[default7]: iteration 316/ 3814 | consumed samples: 161792 | consumed tokens: 331350016 | elapsed time per iteration (s): 6.00 | learning rate: 4.595E-04 | global batch size: 512 | lm loss: 6.435150E+00 | loss scale: 4096.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 317/ 3814 | consumed samples: 162304 | consumed tokens: 332398592 | elapsed time per iteration (s): 5.98 | learning rate: 4.609E-04 | global batch size: 512 | lm loss: 6.441476E+00 | loss scale: 4096.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.662 | TFLOPs: 64.70 | +[default7]: iteration 318/ 3814 | consumed samples: 162816 | consumed tokens: 333447168 | elapsed time per iteration (s): 5.97 | learning rate: 4.624E-04 | global batch size: 512 | lm loss: 6.444716E+00 | loss scale: 4096.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.760 | TFLOPs: 64.78 | +[default7]: iteration 319/ 3814 | consumed samples: 163328 | consumed tokens: 334495744 | elapsed time per iteration (s): 5.97 | learning rate: 4.638E-04 | global batch size: 512 | lm loss: 6.425415E+00 | loss scale: 4096.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.778 | TFLOPs: 64.79 | +[default7]: iteration 320/ 3814 | consumed samples: 163840 | consumed tokens: 335544320 | elapsed time per iteration (s): 5.94 | learning rate: 4.653E-04 | global batch size: 512 | lm loss: 6.446612E+00 | loss scale: 4096.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.182 | TFLOPs: 65.09 | +[default7]: iteration 321/ 3814 | consumed samples: 164352 | consumed tokens: 336592896 | elapsed time per iteration (s): 5.98 | learning rate: 4.667E-04 | global batch size: 512 | lm loss: 6.431455E+00 | loss scale: 4096.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.662 | TFLOPs: 64.70 | +[default7]: iteration 322/ 3814 | consumed samples: 164864 | consumed tokens: 337641472 | elapsed time per iteration (s): 5.97 | learning rate: 4.682E-04 | global batch size: 512 | lm loss: 6.403274E+00 | loss scale: 4096.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.820 | TFLOPs: 64.82 | +[default7]: iteration 323/ 3814 | consumed samples: 165376 | consumed tokens: 338690048 | elapsed time per iteration (s): 5.99 | learning rate: 4.697E-04 | global batch size: 512 | lm loss: 6.401222E+00 | loss scale: 4096.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.411 | TFLOPs: 64.51 | +[default7]: iteration 324/ 3814 | consumed samples: 165888 | consumed tokens: 339738624 | elapsed time per iteration (s): 5.99 | learning rate: 4.711E-04 | global batch size: 512 | lm loss: 6.362503E+00 | loss scale: 4096.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.529 | TFLOPs: 64.60 | +[default7]: iteration 325/ 3814 | consumed samples: 166400 | consumed tokens: 340787200 | elapsed time per iteration (s): 5.96 | learning rate: 4.726E-04 | global batch size: 512 | lm loss: 6.388806E+00 | loss scale: 4096.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.845 | TFLOPs: 64.84 | +[default7]: iteration 326/ 3814 | consumed samples: 166912 | consumed tokens: 341835776 | elapsed time per iteration (s): 5.98 | learning rate: 4.740E-04 | global batch size: 512 | lm loss: 6.409959E+00 | loss scale: 4096.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.600 | TFLOPs: 64.65 | +[default7]: iteration 327/ 3814 | consumed samples: 167424 | consumed tokens: 342884352 | elapsed time per iteration (s): 5.98 | learning rate: 4.755E-04 | global batch size: 512 | lm loss: 6.439007E+00 | loss scale: 4096.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.560 | TFLOPs: 64.62 | +[default7]: iteration 328/ 3814 | consumed samples: 167936 | consumed tokens: 343932928 | elapsed time per iteration (s): 5.67 | learning rate: 4.769E-04 | global batch size: 512 | lm loss: 6.417387E+00 | loss scale: 4096.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.292 | TFLOPs: 68.20 | +[default7]: iteration 329/ 3814 | consumed samples: 168448 | consumed tokens: 344981504 | elapsed time per iteration (s): 5.94 | learning rate: 4.784E-04 | global batch size: 512 | lm loss: 6.370703E+00 | loss scale: 4096.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.223 | TFLOPs: 65.12 | +[default7]: iteration 330/ 3814 | consumed samples: 168960 | consumed tokens: 346030080 | elapsed time per iteration (s): 6.02 | learning rate: 4.798E-04 | global batch size: 512 | lm loss: 6.393504E+00 | loss scale: 4096.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.091 | TFLOPs: 64.27 | +[default7]: iteration 331/ 3814 | consumed samples: 169472 | consumed tokens: 347078656 | elapsed time per iteration (s): 5.97 | learning rate: 4.813E-04 | global batch size: 512 | lm loss: 6.369293E+00 | loss scale: 4096.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.784 | TFLOPs: 64.79 | +[default7]: iteration 332/ 3814 | consumed samples: 169984 | consumed tokens: 348127232 | elapsed time per iteration (s): 5.98 | learning rate: 4.827E-04 | global batch size: 512 | lm loss: 6.354961E+00 | loss scale: 4096.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.661 | TFLOPs: 64.70 | +[default7]: iteration 333/ 3814 | consumed samples: 170496 | consumed tokens: 349175808 | elapsed time per iteration (s): 6.00 | learning rate: 4.842E-04 | global batch size: 512 | lm loss: 6.370229E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.318 | TFLOPs: 64.44 | +[default7]: iteration 334/ 3814 | consumed samples: 171008 | consumed tokens: 350224384 | elapsed time per iteration (s): 6.00 | learning rate: 4.856E-04 | global batch size: 512 | lm loss: 6.378094E+00 | loss scale: 4096.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.272 | TFLOPs: 64.41 | +[default7]: iteration 335/ 3814 | consumed samples: 171520 | consumed tokens: 351272960 | elapsed time per iteration (s): 6.01 | learning rate: 4.871E-04 | global batch size: 512 | lm loss: 6.330650E+00 | loss scale: 4096.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.183 | TFLOPs: 64.34 | +[default7]: iteration 336/ 3814 | consumed samples: 172032 | consumed tokens: 352321536 | elapsed time per iteration (s): 6.07 | learning rate: 4.886E-04 | global batch size: 512 | lm loss: 6.326427E+00 | loss scale: 4096.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.324 | TFLOPs: 63.69 | +[default7]: iteration 337/ 3814 | consumed samples: 172544 | consumed tokens: 353370112 | elapsed time per iteration (s): 6.08 | learning rate: 4.900E-04 | global batch size: 512 | lm loss: 6.314431E+00 | loss scale: 4096.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.175 | TFLOPs: 63.58 | +[default7]: iteration 338/ 3814 | consumed samples: 173056 | consumed tokens: 354418688 | elapsed time per iteration (s): 5.98 | learning rate: 4.915E-04 | global batch size: 512 | lm loss: 6.307499E+00 | loss scale: 4096.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.553 | TFLOPs: 64.62 | +[default7]: iteration 339/ 3814 | consumed samples: 173568 | consumed tokens: 355467264 | elapsed time per iteration (s): 5.92 | learning rate: 4.929E-04 | global batch size: 512 | lm loss: 6.324943E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.553 | TFLOPs: 65.37 | +[default7]: iteration 340/ 3814 | consumed samples: 174080 | consumed tokens: 356515840 | elapsed time per iteration (s): 6.18 | learning rate: 4.944E-04 | global batch size: 512 | lm loss: 6.289916E+00 | loss scale: 4096.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.856 | TFLOPs: 62.58 | +[default7]: iteration 341/ 3814 | consumed samples: 174592 | consumed tokens: 357564416 | elapsed time per iteration (s): 6.15 | learning rate: 4.958E-04 | global batch size: 512 | lm loss: 6.324367E+00 | loss scale: 4096.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.231 | TFLOPs: 62.87 | +[default7]: iteration 342/ 3814 | consumed samples: 175104 | consumed tokens: 358612992 | elapsed time per iteration (s): 6.08 | learning rate: 4.973E-04 | global batch size: 512 | lm loss: 6.300416E+00 | loss scale: 4096.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.257 | TFLOPs: 63.64 | +[default7]: iteration 343/ 3814 | consumed samples: 175616 | consumed tokens: 359661568 | elapsed time per iteration (s): 6.18 | learning rate: 4.987E-04 | global batch size: 512 | lm loss: 6.282803E+00 | loss scale: 4096.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.874 | TFLOPs: 62.60 | +[default7]: iteration 344/ 3814 | consumed samples: 176128 | consumed tokens: 360710144 | elapsed time per iteration (s): 6.11 | learning rate: 5.002E-04 | global batch size: 512 | lm loss: 6.312513E+00 | loss scale: 4096.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.799 | TFLOPs: 63.29 | +[default7]: iteration 345/ 3814 | consumed samples: 176640 | consumed tokens: 361758720 | elapsed time per iteration (s): 6.06 | learning rate: 5.016E-04 | global batch size: 512 | lm loss: 6.304377E+00 | loss scale: 4096.0 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.492 | TFLOPs: 63.82 | +[default7]: iteration 346/ 3814 | consumed samples: 177152 | consumed tokens: 362807296 | elapsed time per iteration (s): 6.11 | learning rate: 5.031E-04 | global batch size: 512 | lm loss: 6.298518E+00 | loss scale: 4096.0 | grad norm: 0.288 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.827 | TFLOPs: 63.32 | +[default7]: iteration 347/ 3814 | consumed samples: 177664 | consumed tokens: 363855872 | elapsed time per iteration (s): 6.00 | learning rate: 5.045E-04 | global batch size: 512 | lm loss: 6.263456E+00 | loss scale: 4096.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.312 | TFLOPs: 64.44 | +[default7]: iteration 348/ 3814 | consumed samples: 178176 | consumed tokens: 364904448 | elapsed time per iteration (s): 6.01 | learning rate: 5.060E-04 | global batch size: 512 | lm loss: 6.303871E+00 | loss scale: 4096.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.231 | TFLOPs: 64.38 | +[default7]: iteration 349/ 3814 | consumed samples: 178688 | consumed tokens: 365953024 | elapsed time per iteration (s): 5.94 | learning rate: 5.075E-04 | global batch size: 512 | lm loss: 6.284752E+00 | loss scale: 4096.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.127 | TFLOPs: 65.05 | +[default7]: iteration 350/ 3814 | consumed samples: 179200 | consumed tokens: 367001600 | elapsed time per iteration (s): 5.92 | learning rate: 5.089E-04 | global batch size: 512 | lm loss: 6.262528E+00 | loss scale: 4096.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.462 | TFLOPs: 65.31 | +[default7]: iteration 351/ 3814 | consumed samples: 179712 | consumed tokens: 368050176 | elapsed time per iteration (s): 5.97 | learning rate: 5.104E-04 | global batch size: 512 | lm loss: 6.290186E+00 | loss scale: 4096.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.776 | TFLOPs: 64.79 | +[default7]: iteration 352/ 3814 | consumed samples: 180224 | consumed tokens: 369098752 | elapsed time per iteration (s): 6.00 | learning rate: 5.118E-04 | global batch size: 512 | lm loss: 6.269284E+00 | loss scale: 4096.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.369 | TFLOPs: 64.48 | +[default7]: iteration 353/ 3814 | consumed samples: 180736 | consumed tokens: 370147328 | elapsed time per iteration (s): 6.00 | learning rate: 5.133E-04 | global batch size: 512 | lm loss: 6.230982E+00 | loss scale: 4096.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.343 | TFLOPs: 64.46 | +[default7]: iteration 354/ 3814 | consumed samples: 181248 | consumed tokens: 371195904 | elapsed time per iteration (s): 6.02 | learning rate: 5.147E-04 | global batch size: 512 | lm loss: 6.246268E+00 | loss scale: 4096.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.108 | TFLOPs: 64.28 | +[default7]: iteration 355/ 3814 | consumed samples: 181760 | consumed tokens: 372244480 | elapsed time per iteration (s): 5.87 | learning rate: 5.162E-04 | global batch size: 512 | lm loss: 6.236328E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.242 | TFLOPs: 65.90 | +[default7]: iteration 356/ 3814 | consumed samples: 182272 | consumed tokens: 373293056 | elapsed time per iteration (s): 6.15 | learning rate: 5.176E-04 | global batch size: 512 | lm loss: 6.208609E+00 | loss scale: 4096.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.285 | TFLOPs: 62.91 | +[default7]: iteration 357/ 3814 | consumed samples: 182784 | consumed tokens: 374341632 | elapsed time per iteration (s): 5.96 | learning rate: 5.191E-04 | global batch size: 512 | lm loss: 6.232487E+00 | loss scale: 4096.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.852 | TFLOPs: 64.85 | +[default7]: iteration 358/ 3814 | consumed samples: 183296 | consumed tokens: 375390208 | elapsed time per iteration (s): 5.93 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.197948E+00 | loss scale: 4096.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.315 | TFLOPs: 65.19 | +[default7]: iteration 359/ 3814 | consumed samples: 183808 | consumed tokens: 376438784 | elapsed time per iteration (s): 5.93 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.172963E+00 | loss scale: 4096.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.407 | TFLOPs: 65.26 | +[default7]: iteration 360/ 3814 | consumed samples: 184320 | consumed tokens: 377487360 | elapsed time per iteration (s): 6.07 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.173426E+00 | loss scale: 4096.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.413 | TFLOPs: 63.76 | +[default7]: iteration 361/ 3814 | consumed samples: 184832 | consumed tokens: 378535936 | elapsed time per iteration (s): 6.09 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.185473E+00 | loss scale: 4096.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.015 | TFLOPs: 63.46 | +[default7]: iteration 362/ 3814 | consumed samples: 185344 | consumed tokens: 379584512 | elapsed time per iteration (s): 6.10 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.174919E+00 | loss scale: 4096.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.961 | TFLOPs: 63.42 | +[default7]: iteration 363/ 3814 | consumed samples: 185856 | consumed tokens: 380633088 | elapsed time per iteration (s): 6.17 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.192150E+00 | loss scale: 4096.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.010 | TFLOPs: 62.70 | +[default7]: iteration 364/ 3814 | consumed samples: 186368 | consumed tokens: 381681664 | elapsed time per iteration (s): 5.96 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.170972E+00 | loss scale: 4096.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.835 | TFLOPs: 64.83 | +[default7]: iteration 365/ 3814 | consumed samples: 186880 | consumed tokens: 382730240 | elapsed time per iteration (s): 5.95 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.167213E+00 | loss scale: 4096.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.115 | TFLOPs: 65.04 | +[default7]: iteration 366/ 3814 | consumed samples: 187392 | consumed tokens: 383778816 | elapsed time per iteration (s): 5.99 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.171658E+00 | loss scale: 4096.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.406 | TFLOPs: 64.51 | +[default7]: iteration 367/ 3814 | consumed samples: 187904 | consumed tokens: 384827392 | elapsed time per iteration (s): 6.11 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.180080E+00 | loss scale: 4096.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.801 | TFLOPs: 63.30 | +[default7]: iteration 368/ 3814 | consumed samples: 188416 | consumed tokens: 385875968 | elapsed time per iteration (s): 5.99 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.155130E+00 | loss scale: 4096.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.459 | TFLOPs: 64.55 | +[default7]: iteration 369/ 3814 | consumed samples: 188928 | consumed tokens: 386924544 | elapsed time per iteration (s): 5.91 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.166196E+00 | loss scale: 4096.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.614 | TFLOPs: 65.42 | +[default7]: iteration 370/ 3814 | consumed samples: 189440 | consumed tokens: 387973120 | elapsed time per iteration (s): 5.94 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.137931E+00 | loss scale: 4096.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.267 | TFLOPs: 65.16 | +[default7]: iteration 371/ 3814 | consumed samples: 189952 | consumed tokens: 389021696 | elapsed time per iteration (s): 5.91 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.152634E+00 | loss scale: 4096.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.652 | TFLOPs: 65.45 | +[default7]: iteration 372/ 3814 | consumed samples: 190464 | consumed tokens: 390070272 | elapsed time per iteration (s): 5.90 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.170305E+00 | loss scale: 4096.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.724 | TFLOPs: 65.50 | +[default7]: iteration 373/ 3814 | consumed samples: 190976 | consumed tokens: 391118848 | elapsed time per iteration (s): 6.13 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.169741E+00 | loss scale: 4096.0 | grad norm: 0.320 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.474 | TFLOPs: 63.05 | +[default7]: iteration 374/ 3814 | consumed samples: 191488 | consumed tokens: 392167424 | elapsed time per iteration (s): 6.16 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.172554E+00 | loss scale: 4096.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.082 | TFLOPs: 62.75 | +[default7]: iteration 375/ 3814 | consumed samples: 192000 | consumed tokens: 393216000 | elapsed time per iteration (s): 5.94 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.150636E+00 | loss scale: 4096.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.185 | TFLOPs: 65.10 | +[default7]: iteration 376/ 3814 | consumed samples: 192512 | consumed tokens: 394264576 | elapsed time per iteration (s): 6.16 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.137257E+00 | loss scale: 4096.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.155 | TFLOPs: 62.81 | +[default7]: iteration 377/ 3814 | consumed samples: 193024 | consumed tokens: 395313152 | elapsed time per iteration (s): 6.15 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.133143E+00 | loss scale: 4096.0 | grad norm: 0.333 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.211 | TFLOPs: 62.85 | +[default7]: iteration 378/ 3814 | consumed samples: 193536 | consumed tokens: 396361728 | elapsed time per iteration (s): 5.97 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.109514E+00 | loss scale: 4096.0 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.824 | TFLOPs: 64.82 | +[default7]: iteration 379/ 3814 | consumed samples: 194048 | consumed tokens: 397410304 | elapsed time per iteration (s): 5.96 | learning rate: 5.200E-04 | global batch size: 512 | lm loss: 6.130941E+00 | loss scale: 4096.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.945 | TFLOPs: 64.92 | +[default7]: iteration 380/ 3814 | consumed samples: 194560 | consumed tokens: 398458880 | elapsed time per iteration (s): 6.01 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.119425E+00 | loss scale: 4096.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.168 | TFLOPs: 64.33 | +[default7]: iteration 381/ 3814 | consumed samples: 195072 | consumed tokens: 399507456 | elapsed time per iteration (s): 5.96 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.126366E+00 | loss scale: 4096.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.915 | TFLOPs: 64.89 | +[default7]: iteration 382/ 3814 | consumed samples: 195584 | consumed tokens: 400556032 | elapsed time per iteration (s): 5.91 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.105669E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.646 | TFLOPs: 65.44 | +[default7]: iteration 383/ 3814 | consumed samples: 196096 | consumed tokens: 401604608 | elapsed time per iteration (s): 5.95 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.118378E+00 | loss scale: 4096.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.052 | TFLOPs: 65.00 | +[default7]: iteration 384/ 3814 | consumed samples: 196608 | consumed tokens: 402653184 | elapsed time per iteration (s): 5.87 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.098251E+00 | loss scale: 4096.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.294 | TFLOPs: 65.93 | +[default7]: iteration 385/ 3814 | consumed samples: 197120 | consumed tokens: 403701760 | elapsed time per iteration (s): 5.93 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.083840E+00 | loss scale: 4096.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.364 | TFLOPs: 65.23 | +[default7]: iteration 386/ 3814 | consumed samples: 197632 | consumed tokens: 404750336 | elapsed time per iteration (s): 5.64 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.092677E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.752 | TFLOPs: 68.55 | +[default7]: iteration 387/ 3814 | consumed samples: 198144 | consumed tokens: 405798912 | elapsed time per iteration (s): 5.92 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.061256E+00 | loss scale: 4096.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.481 | TFLOPs: 65.32 | +[default7]: iteration 388/ 3814 | consumed samples: 198656 | consumed tokens: 406847488 | elapsed time per iteration (s): 5.91 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.078131E+00 | loss scale: 4096.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.567 | TFLOPs: 65.39 | +[default7]: iteration 389/ 3814 | consumed samples: 199168 | consumed tokens: 407896064 | elapsed time per iteration (s): 5.93 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.036090E+00 | loss scale: 4096.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.376 | TFLOPs: 65.24 | +[default7]: iteration 390/ 3814 | consumed samples: 199680 | consumed tokens: 408944640 | elapsed time per iteration (s): 5.95 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.083637E+00 | loss scale: 4096.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.002 | TFLOPs: 64.96 | +[default7]: iteration 391/ 3814 | consumed samples: 200192 | consumed tokens: 409993216 | elapsed time per iteration (s): 5.94 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.077412E+00 | loss scale: 4096.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.167 | TFLOPs: 65.08 | +[default7]: iteration 392/ 3814 | consumed samples: 200704 | consumed tokens: 411041792 | elapsed time per iteration (s): 5.92 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.014859E+00 | loss scale: 4096.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.547 | TFLOPs: 65.37 | +[default7]: iteration 393/ 3814 | consumed samples: 201216 | consumed tokens: 412090368 | elapsed time per iteration (s): 5.94 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.055513E+00 | loss scale: 4096.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.130 | TFLOPs: 65.06 | +[default7]: iteration 394/ 3814 | consumed samples: 201728 | consumed tokens: 413138944 | elapsed time per iteration (s): 5.93 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.055523E+00 | loss scale: 4096.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.397 | TFLOPs: 65.26 | +[default7]: iteration 395/ 3814 | consumed samples: 202240 | consumed tokens: 414187520 | elapsed time per iteration (s): 5.86 | learning rate: 5.199E-04 | global batch size: 512 | lm loss: 6.051373E+00 | loss scale: 4096.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.348 | TFLOPs: 65.98 | +[default7]: iteration 396/ 3814 | consumed samples: 202752 | consumed tokens: 415236096 | elapsed time per iteration (s): 5.97 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.049358E+00 | loss scale: 4096.0 | grad norm: 0.328 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.828 | TFLOPs: 64.83 | +[default7]: iteration 397/ 3814 | consumed samples: 203264 | consumed tokens: 416284672 | elapsed time per iteration (s): 5.97 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.065806E+00 | loss scale: 4096.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.810 | TFLOPs: 64.81 | +[default7]: iteration 398/ 3814 | consumed samples: 203776 | consumed tokens: 417333248 | elapsed time per iteration (s): 5.95 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.039520E+00 | loss scale: 4096.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.086 | TFLOPs: 65.02 | +[default7]: iteration 399/ 3814 | consumed samples: 204288 | consumed tokens: 418381824 | elapsed time per iteration (s): 5.97 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.044620E+00 | loss scale: 4096.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.711 | TFLOPs: 64.74 | +[default7]: iteration 400/ 3814 | consumed samples: 204800 | consumed tokens: 419430400 | elapsed time per iteration (s): 5.98 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.027182E+00 | loss scale: 4096.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.569 | TFLOPs: 64.63 | +[default7]: iteration 401/ 3814 | consumed samples: 205312 | consumed tokens: 420478976 | elapsed time per iteration (s): 5.93 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.022214E+00 | loss scale: 4096.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.353 | TFLOPs: 65.22 | +[default7]: iteration 402/ 3814 | consumed samples: 205824 | consumed tokens: 421527552 | elapsed time per iteration (s): 5.93 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.026709E+00 | loss scale: 4096.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.377 | TFLOPs: 65.24 | +[default7]: iteration 403/ 3814 | consumed samples: 206336 | consumed tokens: 422576128 | elapsed time per iteration (s): 5.91 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.009973E+00 | loss scale: 4096.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.615 | TFLOPs: 65.42 | +[default7]: iteration 404/ 3814 | consumed samples: 206848 | consumed tokens: 423624704 | elapsed time per iteration (s): 5.98 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 5.996346E+00 | loss scale: 4096.0 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 405/ 3814 | consumed samples: 207360 | consumed tokens: 424673280 | elapsed time per iteration (s): 5.91 | learning rate: 5.198E-04 | global batch size: 512 | lm loss: 6.023770E+00 | loss scale: 4096.0 | grad norm: 0.392 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.579 | TFLOPs: 65.39 | +[default7]: iteration 406/ 3814 | consumed samples: 207872 | consumed tokens: 425721856 | elapsed time per iteration (s): 5.95 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 6.028950E+00 | loss scale: 4096.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.018 | TFLOPs: 64.97 | +[default7]: iteration 407/ 3814 | consumed samples: 208384 | consumed tokens: 426770432 | elapsed time per iteration (s): 5.95 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 6.033617E+00 | loss scale: 4096.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.122 | TFLOPs: 65.05 | +[default7]: iteration 408/ 3814 | consumed samples: 208896 | consumed tokens: 427819008 | elapsed time per iteration (s): 5.90 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 5.996882E+00 | loss scale: 4096.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.806 | TFLOPs: 65.57 | +[default7]: iteration 409/ 3814 | consumed samples: 209408 | consumed tokens: 428867584 | elapsed time per iteration (s): 5.94 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 6.014422E+00 | loss scale: 4096.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.235 | TFLOPs: 65.13 | +[default7]: iteration 410/ 3814 | consumed samples: 209920 | consumed tokens: 429916160 | elapsed time per iteration (s): 5.99 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 5.993324E+00 | loss scale: 4096.0 | grad norm: 0.278 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.519 | TFLOPs: 64.59 | +[default7]: iteration 411/ 3814 | consumed samples: 210432 | consumed tokens: 430964736 | elapsed time per iteration (s): 5.93 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 5.972562E+00 | loss scale: 4096.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.309 | TFLOPs: 65.19 | +[default7]: iteration 412/ 3814 | consumed samples: 210944 | consumed tokens: 432013312 | elapsed time per iteration (s): 5.96 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 5.972069E+00 | loss scale: 4096.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.866 | TFLOPs: 64.86 | +[default7]: iteration 413/ 3814 | consumed samples: 211456 | consumed tokens: 433061888 | elapsed time per iteration (s): 5.83 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 5.985733E+00 | loss scale: 4096.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.844 | TFLOPs: 66.35 | +[default7]: iteration 414/ 3814 | consumed samples: 211968 | consumed tokens: 434110464 | elapsed time per iteration (s): 5.89 | learning rate: 5.197E-04 | global batch size: 512 | lm loss: 5.949094E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.966 | TFLOPs: 65.69 | +[default7]: iteration 415/ 3814 | consumed samples: 212480 | consumed tokens: 435159040 | elapsed time per iteration (s): 5.94 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.955163E+00 | loss scale: 4096.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.195 | TFLOPs: 65.10 | +[default7]: iteration 416/ 3814 | consumed samples: 212992 | consumed tokens: 436207616 | elapsed time per iteration (s): 5.90 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.946013E+00 | loss scale: 4096.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.722 | TFLOPs: 65.50 | +[default7]: iteration 417/ 3814 | consumed samples: 213504 | consumed tokens: 437256192 | elapsed time per iteration (s): 5.93 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.923220E+00 | loss scale: 4096.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.373 | TFLOPs: 65.24 | +[default7]: iteration 418/ 3814 | consumed samples: 214016 | consumed tokens: 438304768 | elapsed time per iteration (s): 5.96 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.928411E+00 | loss scale: 4096.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.934 | TFLOPs: 64.91 | +[default7]: iteration 419/ 3814 | consumed samples: 214528 | consumed tokens: 439353344 | elapsed time per iteration (s): 5.92 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.950526E+00 | loss scale: 4096.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.450 | TFLOPs: 65.30 | +[default7]: iteration 420/ 3814 | consumed samples: 215040 | consumed tokens: 440401920 | elapsed time per iteration (s): 5.94 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.951869E+00 | loss scale: 4096.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.203 | TFLOPs: 65.11 | +[default7]: iteration 421/ 3814 | consumed samples: 215552 | consumed tokens: 441450496 | elapsed time per iteration (s): 5.91 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.939289E+00 | loss scale: 4096.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.562 | TFLOPs: 65.38 | +[default7]: iteration 422/ 3814 | consumed samples: 216064 | consumed tokens: 442499072 | elapsed time per iteration (s): 5.93 | learning rate: 5.196E-04 | global batch size: 512 | lm loss: 5.929833E+00 | loss scale: 4096.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.323 | TFLOPs: 65.20 | +[default7]: iteration 423/ 3814 | consumed samples: 216576 | consumed tokens: 443547648 | elapsed time per iteration (s): 5.93 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.906347E+00 | loss scale: 4096.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.362 | TFLOPs: 65.23 | +[default7]: iteration 424/ 3814 | consumed samples: 217088 | consumed tokens: 444596224 | elapsed time per iteration (s): 5.98 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.942788E+00 | loss scale: 4096.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.557 | TFLOPs: 64.62 | +[default7]: iteration 425/ 3814 | consumed samples: 217600 | consumed tokens: 445644800 | elapsed time per iteration (s): 5.91 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.923792E+00 | loss scale: 4096.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.693 | TFLOPs: 65.48 | +[default7]: iteration 426/ 3814 | consumed samples: 218112 | consumed tokens: 446693376 | elapsed time per iteration (s): 5.95 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.911000E+00 | loss scale: 4096.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.991 | TFLOPs: 64.95 | +[default7]: iteration 427/ 3814 | consumed samples: 218624 | consumed tokens: 447741952 | elapsed time per iteration (s): 5.94 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.901332E+00 | loss scale: 4096.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.221 | TFLOPs: 65.12 | +[default7]: iteration 428/ 3814 | consumed samples: 219136 | consumed tokens: 448790528 | elapsed time per iteration (s): 5.96 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.924469E+00 | loss scale: 4096.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.907 | TFLOPs: 64.89 | +[default7]: iteration 429/ 3814 | consumed samples: 219648 | consumed tokens: 449839104 | elapsed time per iteration (s): 5.93 | learning rate: 5.195E-04 | global batch size: 512 | lm loss: 5.900429E+00 | loss scale: 4096.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.391 | TFLOPs: 65.25 | +[default7]: iteration 430/ 3814 | consumed samples: 220160 | consumed tokens: 450887680 | elapsed time per iteration (s): 5.93 | learning rate: 5.194E-04 | global batch size: 512 | lm loss: 5.907557E+00 | loss scale: 4096.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.399 | TFLOPs: 65.26 | +[default7]: iteration 431/ 3814 | consumed samples: 220672 | consumed tokens: 451936256 | elapsed time per iteration (s): 5.96 | learning rate: 5.194E-04 | global batch size: 512 | lm loss: 5.851026E+00 | loss scale: 4096.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.926 | TFLOPs: 64.90 | +[default7]: iteration 432/ 3814 | consumed samples: 221184 | consumed tokens: 452984832 | elapsed time per iteration (s): 5.93 | learning rate: 5.194E-04 | global batch size: 512 | lm loss: 5.875920E+00 | loss scale: 4096.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.275 | TFLOPs: 65.16 | +[default7]: iteration 433/ 3814 | consumed samples: 221696 | consumed tokens: 454033408 | elapsed time per iteration (s): 5.97 | learning rate: 5.194E-04 | global batch size: 512 | lm loss: 5.864797E+00 | loss scale: 4096.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.693 | TFLOPs: 64.72 | +[default7]: iteration 434/ 3814 | consumed samples: 222208 | consumed tokens: 455081984 | elapsed time per iteration (s): 5.97 | learning rate: 5.194E-04 | global batch size: 512 | lm loss: 5.873414E+00 | loss scale: 4096.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.829 | TFLOPs: 64.83 | +[default7]: iteration 435/ 3814 | consumed samples: 222720 | consumed tokens: 456130560 | elapsed time per iteration (s): 5.97 | learning rate: 5.194E-04 | global batch size: 512 | lm loss: 5.871884E+00 | loss scale: 4096.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.774 | TFLOPs: 64.79 | +[default7]: iteration 436/ 3814 | consumed samples: 223232 | consumed tokens: 457179136 | elapsed time per iteration (s): 5.96 | learning rate: 5.193E-04 | global batch size: 512 | lm loss: 5.884535E+00 | loss scale: 4096.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.926 | TFLOPs: 64.90 | +[default7]: iteration 437/ 3814 | consumed samples: 223744 | consumed tokens: 458227712 | elapsed time per iteration (s): 5.94 | learning rate: 5.193E-04 | global batch size: 512 | lm loss: 5.839216E+00 | loss scale: 4096.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.182 | TFLOPs: 65.09 | +[default7]: iteration 438/ 3814 | consumed samples: 224256 | consumed tokens: 459276288 | elapsed time per iteration (s): 5.95 | learning rate: 5.193E-04 | global batch size: 512 | lm loss: 5.861042E+00 | loss scale: 4096.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.065 | TFLOPs: 65.01 | +[default7]: iteration 439/ 3814 | consumed samples: 224768 | consumed tokens: 460324864 | elapsed time per iteration (s): 6.00 | learning rate: 5.193E-04 | global batch size: 512 | lm loss: 5.871428E+00 | loss scale: 4096.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.340 | TFLOPs: 64.46 | +[default7]: iteration 440/ 3814 | consumed samples: 225280 | consumed tokens: 461373440 | elapsed time per iteration (s): 6.00 | learning rate: 5.193E-04 | global batch size: 512 | lm loss: 5.838655E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.334 | TFLOPs: 64.45 | +[default7]: iteration 441/ 3814 | consumed samples: 225792 | consumed tokens: 462422016 | elapsed time per iteration (s): 6.11 | learning rate: 5.193E-04 | global batch size: 512 | lm loss: 5.854117E+00 | loss scale: 4096.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.782 | TFLOPs: 63.28 | +[default7]: iteration 442/ 3814 | consumed samples: 226304 | consumed tokens: 463470592 | elapsed time per iteration (s): 6.17 | learning rate: 5.192E-04 | global batch size: 512 | lm loss: 5.874722E+00 | loss scale: 4096.0 | grad norm: 0.326 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.971 | TFLOPs: 62.67 | +[default7]: iteration 443/ 3814 | consumed samples: 226816 | consumed tokens: 464519168 | elapsed time per iteration (s): 5.92 | learning rate: 5.192E-04 | global batch size: 512 | lm loss: 5.854773E+00 | loss scale: 4096.0 | grad norm: 0.338 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.530 | TFLOPs: 65.36 | +[default7]: iteration 444/ 3814 | consumed samples: 227328 | consumed tokens: 465567744 | elapsed time per iteration (s): 5.97 | learning rate: 5.192E-04 | global batch size: 512 | lm loss: 5.853147E+00 | loss scale: 4096.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.778 | TFLOPs: 64.79 | +[default7]: iteration 445/ 3814 | consumed samples: 227840 | consumed tokens: 466616320 | elapsed time per iteration (s): 6.02 | learning rate: 5.192E-04 | global batch size: 512 | lm loss: 5.862232E+00 | loss scale: 4096.0 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.112 | TFLOPs: 64.29 | +[default7]: iteration 446/ 3814 | consumed samples: 228352 | consumed tokens: 467664896 | elapsed time per iteration (s): 5.90 | learning rate: 5.192E-04 | global batch size: 512 | lm loss: 5.865010E+00 | loss scale: 4096.0 | grad norm: 0.291 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.782 | TFLOPs: 65.55 | +[default7]: iteration 447/ 3814 | consumed samples: 228864 | consumed tokens: 468713472 | elapsed time per iteration (s): 5.93 | learning rate: 5.191E-04 | global batch size: 512 | lm loss: 5.840879E+00 | loss scale: 4096.0 | grad norm: 0.351 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.290 | TFLOPs: 65.18 | +[default7]: iteration 448/ 3814 | consumed samples: 229376 | consumed tokens: 469762048 | elapsed time per iteration (s): 6.01 | learning rate: 5.191E-04 | global batch size: 512 | lm loss: 5.895783E+00 | loss scale: 4096.0 | grad norm: 0.420 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.228 | TFLOPs: 64.37 | +[default7]: iteration 449/ 3814 | consumed samples: 229888 | consumed tokens: 470810624 | elapsed time per iteration (s): 5.90 | learning rate: 5.191E-04 | global batch size: 512 | lm loss: 5.839476E+00 | loss scale: 4096.0 | grad norm: 0.413 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.773 | TFLOPs: 65.54 | +[default7]: iteration 450/ 3814 | consumed samples: 230400 | consumed tokens: 471859200 | elapsed time per iteration (s): 5.90 | learning rate: 5.191E-04 | global batch size: 512 | lm loss: 5.855685E+00 | loss scale: 4096.0 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.818 | TFLOPs: 65.57 | +[default7]: iteration 451/ 3814 | consumed samples: 230912 | consumed tokens: 472907776 | elapsed time per iteration (s): 5.95 | learning rate: 5.191E-04 | global batch size: 512 | lm loss: 5.843568E+00 | loss scale: 4096.0 | grad norm: 0.296 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.109 | TFLOPs: 65.04 | +[default7]: iteration 452/ 3814 | consumed samples: 231424 | consumed tokens: 473956352 | elapsed time per iteration (s): 6.00 | learning rate: 5.190E-04 | global batch size: 512 | lm loss: 5.841320E+00 | loss scale: 4096.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.376 | TFLOPs: 64.49 | +[default7]: iteration 453/ 3814 | consumed samples: 231936 | consumed tokens: 475004928 | elapsed time per iteration (s): 5.94 | learning rate: 5.190E-04 | global batch size: 512 | lm loss: 5.816973E+00 | loss scale: 4096.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.238 | TFLOPs: 65.14 | +[default7]: iteration 454/ 3814 | consumed samples: 232448 | consumed tokens: 476053504 | elapsed time per iteration (s): 6.00 | learning rate: 5.190E-04 | global batch size: 512 | lm loss: 5.803047E+00 | loss scale: 4096.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.395 | TFLOPs: 64.50 | +[default7]: iteration 455/ 3814 | consumed samples: 232960 | consumed tokens: 477102080 | elapsed time per iteration (s): 5.94 | learning rate: 5.190E-04 | global batch size: 512 | lm loss: 5.803441E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.216 | TFLOPs: 65.12 | +[default7]: iteration 456/ 3814 | consumed samples: 233472 | consumed tokens: 478150656 | elapsed time per iteration (s): 5.86 | learning rate: 5.190E-04 | global batch size: 512 | lm loss: 5.819914E+00 | loss scale: 4096.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.401 | TFLOPs: 66.01 | +[default7]: iteration 457/ 3814 | consumed samples: 233984 | consumed tokens: 479199232 | elapsed time per iteration (s): 5.97 | learning rate: 5.189E-04 | global batch size: 512 | lm loss: 5.795063E+00 | loss scale: 4096.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.795 | TFLOPs: 64.80 | +[default7]: iteration 458/ 3814 | consumed samples: 234496 | consumed tokens: 480247808 | elapsed time per iteration (s): 5.89 | learning rate: 5.189E-04 | global batch size: 512 | lm loss: 5.804592E+00 | loss scale: 4096.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.914 | TFLOPs: 65.65 | +[default7]: iteration 459/ 3814 | consumed samples: 235008 | consumed tokens: 481296384 | elapsed time per iteration (s): 5.97 | learning rate: 5.189E-04 | global batch size: 512 | lm loss: 5.749132E+00 | loss scale: 4096.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.800 | TFLOPs: 64.81 | +[default7]: iteration 460/ 3814 | consumed samples: 235520 | consumed tokens: 482344960 | elapsed time per iteration (s): 5.93 | learning rate: 5.189E-04 | global batch size: 512 | lm loss: 5.787395E+00 | loss scale: 4096.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.329 | TFLOPs: 65.21 | +[default7]: iteration 461/ 3814 | consumed samples: 236032 | consumed tokens: 483393536 | elapsed time per iteration (s): 5.97 | learning rate: 5.189E-04 | global batch size: 512 | lm loss: 5.771373E+00 | loss scale: 4096.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.827 | TFLOPs: 64.83 | +[default7]: iteration 462/ 3814 | consumed samples: 236544 | consumed tokens: 484442112 | elapsed time per iteration (s): 5.99 | learning rate: 5.188E-04 | global batch size: 512 | lm loss: 5.747844E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.520 | TFLOPs: 64.59 | +[default7]: iteration 463/ 3814 | consumed samples: 237056 | consumed tokens: 485490688 | elapsed time per iteration (s): 5.98 | learning rate: 5.188E-04 | global batch size: 512 | lm loss: 5.754547E+00 | loss scale: 4096.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.656 | TFLOPs: 64.70 | +[default7]: iteration 464/ 3814 | consumed samples: 237568 | consumed tokens: 486539264 | elapsed time per iteration (s): 6.00 | learning rate: 5.188E-04 | global batch size: 512 | lm loss: 5.750267E+00 | loss scale: 4096.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.404 | TFLOPs: 64.51 | +[default7]: iteration 465/ 3814 | consumed samples: 238080 | consumed tokens: 487587840 | elapsed time per iteration (s): 5.96 | learning rate: 5.188E-04 | global batch size: 512 | lm loss: 5.756591E+00 | loss scale: 4096.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.869 | TFLOPs: 64.86 | +[default7]: iteration 466/ 3814 | consumed samples: 238592 | consumed tokens: 488636416 | elapsed time per iteration (s): 5.95 | learning rate: 5.187E-04 | global batch size: 512 | lm loss: 5.789564E+00 | loss scale: 4096.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.050 | TFLOPs: 64.99 | +[default7]: iteration 467/ 3814 | consumed samples: 239104 | consumed tokens: 489684992 | elapsed time per iteration (s): 5.99 | learning rate: 5.187E-04 | global batch size: 512 | lm loss: 5.738799E+00 | loss scale: 4096.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.424 | TFLOPs: 64.52 | +[default7]: iteration 468/ 3814 | consumed samples: 239616 | consumed tokens: 490733568 | elapsed time per iteration (s): 5.83 | learning rate: 5.187E-04 | global batch size: 512 | lm loss: 5.748240E+00 | loss scale: 4096.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.770 | TFLOPs: 66.29 | +[default7]: iteration 469/ 3814 | consumed samples: 240128 | consumed tokens: 491782144 | elapsed time per iteration (s): 5.89 | learning rate: 5.187E-04 | global batch size: 512 | lm loss: 5.726692E+00 | loss scale: 4096.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.947 | TFLOPs: 65.67 | +[default7]: iteration 470/ 3814 | consumed samples: 240640 | consumed tokens: 492830720 | elapsed time per iteration (s): 5.93 | learning rate: 5.186E-04 | global batch size: 512 | lm loss: 5.738469E+00 | loss scale: 4096.0 | grad norm: 0.311 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.271 | TFLOPs: 65.16 | +[default7]: iteration 471/ 3814 | consumed samples: 241152 | consumed tokens: 493879296 | elapsed time per iteration (s): 5.94 | learning rate: 5.186E-04 | global batch size: 512 | lm loss: 5.755281E+00 | loss scale: 4096.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.125 | TFLOPs: 65.05 | +[default7]: iteration 472/ 3814 | consumed samples: 241664 | consumed tokens: 494927872 | elapsed time per iteration (s): 5.96 | learning rate: 5.186E-04 | global batch size: 512 | lm loss: 5.732049E+00 | loss scale: 4096.0 | grad norm: 0.268 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.880 | TFLOPs: 64.87 | +[default7]: iteration 473/ 3814 | consumed samples: 242176 | consumed tokens: 495976448 | elapsed time per iteration (s): 5.91 | learning rate: 5.186E-04 | global batch size: 512 | lm loss: 5.755622E+00 | loss scale: 4096.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.602 | TFLOPs: 65.41 | +[default7]: iteration 474/ 3814 | consumed samples: 242688 | consumed tokens: 497025024 | elapsed time per iteration (s): 5.94 | learning rate: 5.185E-04 | global batch size: 512 | lm loss: 5.745677E+00 | loss scale: 4096.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.195 | TFLOPs: 65.10 | +[default7]: iteration 475/ 3814 | consumed samples: 243200 | consumed tokens: 498073600 | elapsed time per iteration (s): 5.92 | learning rate: 5.185E-04 | global batch size: 512 | lm loss: 5.735449E+00 | loss scale: 4096.0 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.513 | TFLOPs: 65.34 | +[default7]: iteration 476/ 3814 | consumed samples: 243712 | consumed tokens: 499122176 | elapsed time per iteration (s): 5.87 | learning rate: 5.185E-04 | global batch size: 512 | lm loss: 5.739388E+00 | loss scale: 4096.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.175 | TFLOPs: 65.84 | +[default7]: iteration 477/ 3814 | consumed samples: 244224 | consumed tokens: 500170752 | elapsed time per iteration (s): 5.96 | learning rate: 5.185E-04 | global batch size: 512 | lm loss: 5.735055E+00 | loss scale: 4096.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.892 | TFLOPs: 64.88 | +[default7]: iteration 478/ 3814 | consumed samples: 244736 | consumed tokens: 501219328 | elapsed time per iteration (s): 5.90 | learning rate: 5.184E-04 | global batch size: 512 | lm loss: 5.693710E+00 | loss scale: 4096.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.710 | TFLOPs: 65.49 | +[default7]: iteration 479/ 3814 | consumed samples: 245248 | consumed tokens: 502267904 | elapsed time per iteration (s): 5.90 | learning rate: 5.184E-04 | global batch size: 512 | lm loss: 5.701653E+00 | loss scale: 4096.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.843 | TFLOPs: 65.59 | +[default7]: iteration 480/ 3814 | consumed samples: 245760 | consumed tokens: 503316480 | elapsed time per iteration (s): 5.99 | learning rate: 5.184E-04 | global batch size: 512 | lm loss: 5.716685E+00 | loss scale: 4096.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.505 | TFLOPs: 64.58 | +[default7]: iteration 481/ 3814 | consumed samples: 246272 | consumed tokens: 504365056 | elapsed time per iteration (s): 5.96 | learning rate: 5.184E-04 | global batch size: 512 | lm loss: 5.701454E+00 | loss scale: 4096.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.841 | TFLOPs: 64.84 | +[default7]: iteration 482/ 3814 | consumed samples: 246784 | consumed tokens: 505413632 | elapsed time per iteration (s): 5.87 | learning rate: 5.183E-04 | global batch size: 512 | lm loss: 5.691147E+00 | loss scale: 4096.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.185 | TFLOPs: 65.85 | +[default7]: iteration 483/ 3814 | consumed samples: 247296 | consumed tokens: 506462208 | elapsed time per iteration (s): 5.93 | learning rate: 5.183E-04 | global batch size: 512 | lm loss: 5.689941E+00 | loss scale: 4096.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.368 | TFLOPs: 65.23 | +[default7]: iteration 484/ 3814 | consumed samples: 247808 | consumed tokens: 507510784 | elapsed time per iteration (s): 5.84 | learning rate: 5.183E-04 | global batch size: 512 | lm loss: 5.688974E+00 | loss scale: 4096.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.659 | TFLOPs: 66.21 | +[default7]: iteration 485/ 3814 | consumed samples: 248320 | consumed tokens: 508559360 | elapsed time per iteration (s): 5.93 | learning rate: 5.183E-04 | global batch size: 512 | lm loss: 5.685469E+00 | loss scale: 4096.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.269 | TFLOPs: 65.16 | +[default7]: iteration 486/ 3814 | consumed samples: 248832 | consumed tokens: 509607936 | elapsed time per iteration (s): 5.94 | learning rate: 5.182E-04 | global batch size: 512 | lm loss: 5.688913E+00 | loss scale: 4096.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.260 | TFLOPs: 65.15 | +[default7]: iteration 487/ 3814 | consumed samples: 249344 | consumed tokens: 510656512 | elapsed time per iteration (s): 5.93 | learning rate: 5.182E-04 | global batch size: 512 | lm loss: 5.692589E+00 | loss scale: 4096.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.280 | TFLOPs: 65.17 | +[default7]: iteration 488/ 3814 | consumed samples: 249856 | consumed tokens: 511705088 | elapsed time per iteration (s): 5.92 | learning rate: 5.182E-04 | global batch size: 512 | lm loss: 5.669957E+00 | loss scale: 4096.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.464 | TFLOPs: 65.31 | +[default7]: iteration 489/ 3814 | consumed samples: 250368 | consumed tokens: 512753664 | elapsed time per iteration (s): 5.90 | learning rate: 5.181E-04 | global batch size: 512 | lm loss: 5.678488E+00 | loss scale: 4096.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.714 | TFLOPs: 65.50 | +[default7]: iteration 490/ 3814 | consumed samples: 250880 | consumed tokens: 513802240 | elapsed time per iteration (s): 5.93 | learning rate: 5.181E-04 | global batch size: 512 | lm loss: 5.659495E+00 | loss scale: 4096.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.340 | TFLOPs: 65.21 | +[default7]: iteration 491/ 3814 | consumed samples: 251392 | consumed tokens: 514850816 | elapsed time per iteration (s): 5.86 | learning rate: 5.181E-04 | global batch size: 512 | lm loss: 5.630903E+00 | loss scale: 4096.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.304 | TFLOPs: 65.94 | +[default7]: iteration 492/ 3814 | consumed samples: 251904 | consumed tokens: 515899392 | elapsed time per iteration (s): 5.93 | learning rate: 5.181E-04 | global batch size: 512 | lm loss: 5.646753E+00 | loss scale: 4096.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.295 | TFLOPs: 65.18 | +[default7]: iteration 493/ 3814 | consumed samples: 252416 | consumed tokens: 516947968 | elapsed time per iteration (s): 5.91 | learning rate: 5.180E-04 | global batch size: 512 | lm loss: 5.652385E+00 | loss scale: 4096.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.640 | TFLOPs: 65.44 | +[default7]: iteration 494/ 3814 | consumed samples: 252928 | consumed tokens: 517996544 | elapsed time per iteration (s): 5.89 | learning rate: 5.180E-04 | global batch size: 512 | lm loss: 5.642252E+00 | loss scale: 4096.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.883 | TFLOPs: 65.62 | +[default7]: iteration 495/ 3814 | consumed samples: 253440 | consumed tokens: 519045120 | elapsed time per iteration (s): 5.93 | learning rate: 5.180E-04 | global batch size: 512 | lm loss: 5.636043E+00 | loss scale: 4096.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.378 | TFLOPs: 65.24 | +[default7]: iteration 496/ 3814 | consumed samples: 253952 | consumed tokens: 520093696 | elapsed time per iteration (s): 5.96 | learning rate: 5.179E-04 | global batch size: 512 | lm loss: 5.640230E+00 | loss scale: 4096.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.879 | TFLOPs: 64.86 | +[default7]: iteration 497/ 3814 | consumed samples: 254464 | consumed tokens: 521142272 | elapsed time per iteration (s): 6.01 | learning rate: 5.179E-04 | global batch size: 512 | lm loss: 5.634777E+00 | loss scale: 4096.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.138 | TFLOPs: 64.31 | +[default7]: iteration 498/ 3814 | consumed samples: 254976 | consumed tokens: 522190848 | elapsed time per iteration (s): 5.97 | learning rate: 5.179E-04 | global batch size: 512 | lm loss: 5.621488E+00 | loss scale: 4096.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.767 | TFLOPs: 64.78 | +[default7]: iteration 499/ 3814 | consumed samples: 255488 | consumed tokens: 523239424 | elapsed time per iteration (s): 5.91 | learning rate: 5.179E-04 | global batch size: 512 | lm loss: 5.629735E+00 | loss scale: 4096.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.699 | TFLOPs: 65.48 | +[default7]: iteration 500/ 3814 | consumed samples: 256000 | consumed tokens: 524288000 | elapsed time per iteration (s): 5.96 | learning rate: 5.178E-04 | global batch size: 512 | lm loss: 5.633023E+00 | loss scale: 8192.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.850 | TFLOPs: 64.84 | +[default0]:saving checkpoint at iteration 500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 08:22:27,713] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step500 is begin to save! +[default0]:[2023-02-16 08:22:27,717] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:27,717] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:27,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:27,870] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:27,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:27,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:27,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:27,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:27,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:27,931] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:27,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:27,998] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,057] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:27,992] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:27,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,048] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,113] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,104] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,163] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,163] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,220] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,221] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,276] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,283] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,284] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,330] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,330] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,387] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,399] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,466] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,453] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,525] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,509] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,569] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,582] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,582] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,636] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,637] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,625] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,685] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,750] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,741] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,742] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,806] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,807] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:28,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,866] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,801] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,802] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,862] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,924] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,925] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:28,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,922] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:28,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:28,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:28,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:28,986] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,044] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,045] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:29,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,089] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:29,099] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:29,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,268] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,206] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:29,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:29,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,318] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:29,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:29,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,381] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,439] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,434] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:29,488] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,489] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:29,496] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,496] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,544] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 08:22:29,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,611] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 08:22:29,600] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,601] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:29,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_01-model_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:22:29,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 08:22:29,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 08:22:29,731] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_00_model_states.pt +[default0]:[2023-02-16 08:22:29,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 08:22:29,733] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 08:22:29,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,711] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 08:22:29,712] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 08:22:29,713] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_01_model_states.pt +[default1]:[2023-02-16 08:22:29,713] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 08:22:29,715] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:22:29,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 08:22:30,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,240] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,240] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,259] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,260] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,239] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,279] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,300] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,300] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,295] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,295] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,295] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,336] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,322] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,331] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,267] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,373] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,373] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,348] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,334] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,313] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,368] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,362] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,362] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,362] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,349] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,349] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,394] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,406] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,396] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,382] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,398] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,398] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,398] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,371] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,372] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,348] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,425] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,423] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,361] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,361] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,384] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,385] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,428] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,347] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,347] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,347] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,412] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,412] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,378] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,378] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,354] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,422] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,364] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,364] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,385] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,454] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,444] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,456] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,416] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,418] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,418] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,411] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,441] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,441] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,443] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,443] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,460] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,432] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,432] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,412] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,412] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,412] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,411] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default1]:[2023-02-16 08:22:30,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:22:30,422] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:22:30,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,459] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,459] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,473] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,473] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,473] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,433] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default4]:[2023-02-16 08:22:30,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:22:30,545] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:22:30,545] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,531] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,531] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,525] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,525] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default3]:[2023-02-16 08:22:30,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:22:30,526] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:22:30,526] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default5]:[2023-02-16 08:22:30,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:22:30,569] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:22:30,569] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,560] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,601] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,601] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default2]:[2023-02-16 08:22:30,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:22:30,629] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:22:30,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default6]:[2023-02-16 08:22:30,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:22:30,662] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:22:30,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default0]:[2023-02-16 08:22:30,629] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:22:30,629] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:22:30,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:[2023-02-16 08:22:30,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:22:30,690] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step500/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:22:30,690] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step500 is ready now! +[default7]:time (ms) | save-checkpoint: 2979.64 +[default0]: successfully saved checkpoint at iteration 500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]: iteration 501/ 3814 | consumed samples: 256512 | consumed tokens: 525336576 | elapsed time per iteration (s): 8.94 | learning rate: 5.178E-04 | global batch size: 512 | lm loss: 5.613497E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 57.281 | TFLOPs: 43.27 | +[default7]: iteration 502/ 3814 | consumed samples: 257024 | consumed tokens: 526385152 | elapsed time per iteration (s): 5.99 | learning rate: 5.178E-04 | global batch size: 512 | lm loss: 5.640046E+00 | loss scale: 8192.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.451 | TFLOPs: 64.54 | +[default7]: iteration 503/ 3814 | consumed samples: 257536 | consumed tokens: 527433728 | elapsed time per iteration (s): 5.97 | learning rate: 5.177E-04 | global batch size: 512 | lm loss: 5.618315E+00 | loss scale: 8192.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.731 | TFLOPs: 64.75 | +[default7]: iteration 504/ 3814 | consumed samples: 258048 | consumed tokens: 528482304 | elapsed time per iteration (s): 5.95 | learning rate: 5.177E-04 | global batch size: 512 | lm loss: 5.640858E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.087 | TFLOPs: 65.02 | +[default7]: iteration 505/ 3814 | consumed samples: 258560 | consumed tokens: 529530880 | elapsed time per iteration (s): 5.99 | learning rate: 5.177E-04 | global batch size: 512 | lm loss: 5.603507E+00 | loss scale: 8192.0 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.502 | TFLOPs: 64.58 | +[default7]: iteration 506/ 3814 | consumed samples: 259072 | consumed tokens: 530579456 | elapsed time per iteration (s): 5.98 | learning rate: 5.176E-04 | global batch size: 512 | lm loss: 5.627226E+00 | loss scale: 8192.0 | grad norm: 0.340 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.550 | TFLOPs: 64.62 | +[default7]: iteration 507/ 3814 | consumed samples: 259584 | consumed tokens: 531628032 | elapsed time per iteration (s): 5.94 | learning rate: 5.176E-04 | global batch size: 512 | lm loss: 5.625604E+00 | loss scale: 8192.0 | grad norm: 0.334 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.220 | TFLOPs: 65.12 | +[default7]: iteration 508/ 3814 | consumed samples: 260096 | consumed tokens: 532676608 | elapsed time per iteration (s): 5.93 | learning rate: 5.176E-04 | global batch size: 512 | lm loss: 5.646130E+00 | loss scale: 8192.0 | grad norm: 0.389 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.283 | TFLOPs: 65.17 | +[default7]: iteration 509/ 3814 | consumed samples: 260608 | consumed tokens: 533725184 | elapsed time per iteration (s): 5.97 | learning rate: 5.175E-04 | global batch size: 512 | lm loss: 5.651425E+00 | loss scale: 8192.0 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.834 | TFLOPs: 64.83 | +[default7]: iteration 510/ 3814 | consumed samples: 261120 | consumed tokens: 534773760 | elapsed time per iteration (s): 5.94 | learning rate: 5.175E-04 | global batch size: 512 | lm loss: 5.634167E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.245 | TFLOPs: 65.14 | +[default7]: iteration 511/ 3814 | consumed samples: 261632 | consumed tokens: 535822336 | elapsed time per iteration (s): 5.98 | learning rate: 5.175E-04 | global batch size: 512 | lm loss: 5.620042E+00 | loss scale: 8192.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.688 | TFLOPs: 64.72 | +[default7]: iteration 512/ 3814 | consumed samples: 262144 | consumed tokens: 536870912 | elapsed time per iteration (s): 5.98 | learning rate: 5.174E-04 | global batch size: 512 | lm loss: 5.611800E+00 | loss scale: 8192.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.595 | TFLOPs: 64.65 | +[default7]: iteration 513/ 3814 | consumed samples: 262656 | consumed tokens: 537919488 | elapsed time per iteration (s): 5.88 | learning rate: 5.174E-04 | global batch size: 512 | lm loss: 5.581920E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.123 | TFLOPs: 65.80 | +[default7]: iteration 514/ 3814 | consumed samples: 263168 | consumed tokens: 538968064 | elapsed time per iteration (s): 5.90 | learning rate: 5.174E-04 | global batch size: 512 | lm loss: 5.592402E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.709 | TFLOPs: 65.49 | +[default7]: iteration 515/ 3814 | consumed samples: 263680 | consumed tokens: 540016640 | elapsed time per iteration (s): 5.97 | learning rate: 5.173E-04 | global batch size: 512 | lm loss: 5.570735E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.804 | TFLOPs: 64.81 | +[default7]: iteration 516/ 3814 | consumed samples: 264192 | consumed tokens: 541065216 | elapsed time per iteration (s): 5.94 | learning rate: 5.173E-04 | global batch size: 512 | lm loss: 5.555836E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.254 | TFLOPs: 65.15 | +[default7]: iteration 517/ 3814 | consumed samples: 264704 | consumed tokens: 542113792 | elapsed time per iteration (s): 5.94 | learning rate: 5.173E-04 | global batch size: 512 | lm loss: 5.566995E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.202 | TFLOPs: 65.11 | +[default7]: iteration 518/ 3814 | consumed samples: 265216 | consumed tokens: 543162368 | elapsed time per iteration (s): 5.93 | learning rate: 5.172E-04 | global batch size: 512 | lm loss: 5.571459E+00 | loss scale: 8192.0 | grad norm: 0.217 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.344 | TFLOPs: 65.22 | +[default7]: iteration 519/ 3814 | consumed samples: 265728 | consumed tokens: 544210944 | elapsed time per iteration (s): 5.93 | learning rate: 5.172E-04 | global batch size: 512 | lm loss: 5.577075E+00 | loss scale: 8192.0 | grad norm: 0.283 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.295 | TFLOPs: 65.18 | +[default7]: iteration 520/ 3814 | consumed samples: 266240 | consumed tokens: 545259520 | elapsed time per iteration (s): 5.99 | learning rate: 5.172E-04 | global batch size: 512 | lm loss: 5.570069E+00 | loss scale: 8192.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.463 | TFLOPs: 64.55 | +[default7]: iteration 521/ 3814 | consumed samples: 266752 | consumed tokens: 546308096 | elapsed time per iteration (s): 6.03 | learning rate: 5.171E-04 | global batch size: 512 | lm loss: 5.532170E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.905 | TFLOPs: 64.13 | +[default7]: iteration 522/ 3814 | consumed samples: 267264 | consumed tokens: 547356672 | elapsed time per iteration (s): 5.95 | learning rate: 5.171E-04 | global batch size: 512 | lm loss: 5.554663E+00 | loss scale: 8192.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.066 | TFLOPs: 65.01 | +[default7]: iteration 523/ 3814 | consumed samples: 267776 | consumed tokens: 548405248 | elapsed time per iteration (s): 6.00 | learning rate: 5.171E-04 | global batch size: 512 | lm loss: 5.557630E+00 | loss scale: 8192.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.346 | TFLOPs: 64.46 | +[default7]: iteration 524/ 3814 | consumed samples: 268288 | consumed tokens: 549453824 | elapsed time per iteration (s): 5.94 | learning rate: 5.170E-04 | global batch size: 512 | lm loss: 5.551214E+00 | loss scale: 8192.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.198 | TFLOPs: 65.11 | +[default7]: iteration 525/ 3814 | consumed samples: 268800 | consumed tokens: 550502400 | elapsed time per iteration (s): 5.94 | learning rate: 5.170E-04 | global batch size: 512 | lm loss: 5.587984E+00 | loss scale: 8192.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.129 | TFLOPs: 65.05 | +[default7]: iteration 526/ 3814 | consumed samples: 269312 | consumed tokens: 551550976 | elapsed time per iteration (s): 5.96 | learning rate: 5.170E-04 | global batch size: 512 | lm loss: 5.555473E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.918 | TFLOPs: 64.89 | +[default7]: iteration 527/ 3814 | consumed samples: 269824 | consumed tokens: 552599552 | elapsed time per iteration (s): 5.92 | learning rate: 5.169E-04 | global batch size: 512 | lm loss: 5.548758E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.512 | TFLOPs: 65.34 | +[default7]: iteration 528/ 3814 | consumed samples: 270336 | consumed tokens: 553648128 | elapsed time per iteration (s): 5.97 | learning rate: 5.169E-04 | global batch size: 512 | lm loss: 5.562972E+00 | loss scale: 8192.0 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.766 | TFLOPs: 64.78 | +[default7]: iteration 529/ 3814 | consumed samples: 270848 | consumed tokens: 554696704 | elapsed time per iteration (s): 5.98 | learning rate: 5.169E-04 | global batch size: 512 | lm loss: 5.570995E+00 | loss scale: 8192.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.616 | TFLOPs: 64.67 | +[default7]: iteration 530/ 3814 | consumed samples: 271360 | consumed tokens: 555745280 | elapsed time per iteration (s): 5.89 | learning rate: 5.168E-04 | global batch size: 512 | lm loss: 5.526112E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.897 | TFLOPs: 65.63 | +[default7]: iteration 531/ 3814 | consumed samples: 271872 | consumed tokens: 556793856 | elapsed time per iteration (s): 5.96 | learning rate: 5.168E-04 | global batch size: 512 | lm loss: 5.540549E+00 | loss scale: 8192.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.883 | TFLOPs: 64.87 | +[default7]: iteration 532/ 3814 | consumed samples: 272384 | consumed tokens: 557842432 | elapsed time per iteration (s): 5.85 | learning rate: 5.167E-04 | global batch size: 512 | lm loss: 5.524888E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.579 | TFLOPs: 66.15 | +[default7]: iteration 533/ 3814 | consumed samples: 272896 | consumed tokens: 558891008 | elapsed time per iteration (s): 5.90 | learning rate: 5.167E-04 | global batch size: 512 | lm loss: 5.509696E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.774 | TFLOPs: 65.54 | +[default7]: iteration 534/ 3814 | consumed samples: 273408 | consumed tokens: 559939584 | elapsed time per iteration (s): 5.70 | learning rate: 5.167E-04 | global batch size: 512 | lm loss: 5.490677E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.770 | TFLOPs: 67.80 | +[default7]: iteration 535/ 3814 | consumed samples: 273920 | consumed tokens: 560988160 | elapsed time per iteration (s): 5.97 | learning rate: 5.166E-04 | global batch size: 512 | lm loss: 5.503955E+00 | loss scale: 8192.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.809 | TFLOPs: 64.81 | +[default7]: iteration 536/ 3814 | consumed samples: 274432 | consumed tokens: 562036736 | elapsed time per iteration (s): 5.93 | learning rate: 5.166E-04 | global batch size: 512 | lm loss: 5.508466E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.380 | TFLOPs: 65.24 | +[default7]: iteration 537/ 3814 | consumed samples: 274944 | consumed tokens: 563085312 | elapsed time per iteration (s): 6.02 | learning rate: 5.166E-04 | global batch size: 512 | lm loss: 5.497250E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.117 | TFLOPs: 64.29 | +[default7]: iteration 538/ 3814 | consumed samples: 275456 | consumed tokens: 564133888 | elapsed time per iteration (s): 5.94 | learning rate: 5.165E-04 | global batch size: 512 | lm loss: 5.514307E+00 | loss scale: 8192.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.233 | TFLOPs: 65.13 | +[default7]: iteration 539/ 3814 | consumed samples: 275968 | consumed tokens: 565182464 | elapsed time per iteration (s): 5.98 | learning rate: 5.165E-04 | global batch size: 512 | lm loss: 5.513258E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.678 | TFLOPs: 64.71 | +[default7]: iteration 540/ 3814 | consumed samples: 276480 | consumed tokens: 566231040 | elapsed time per iteration (s): 5.69 | learning rate: 5.164E-04 | global batch size: 512 | lm loss: 5.508328E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.989 | TFLOPs: 67.97 | +[default7]: iteration 541/ 3814 | consumed samples: 276992 | consumed tokens: 567279616 | elapsed time per iteration (s): 5.90 | learning rate: 5.164E-04 | global batch size: 512 | lm loss: 5.508415E+00 | loss scale: 8192.0 | grad norm: 0.304 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.798 | TFLOPs: 65.56 | +[default7]: iteration 542/ 3814 | consumed samples: 277504 | consumed tokens: 568328192 | elapsed time per iteration (s): 5.98 | learning rate: 5.164E-04 | global batch size: 512 | lm loss: 5.498875E+00 | loss scale: 8192.0 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.588 | TFLOPs: 64.65 | +[default7]: iteration 543/ 3814 | consumed samples: 278016 | consumed tokens: 569376768 | elapsed time per iteration (s): 5.97 | learning rate: 5.163E-04 | global batch size: 512 | lm loss: 5.503066E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.770 | TFLOPs: 64.78 | +[default7]: iteration 544/ 3814 | consumed samples: 278528 | consumed tokens: 570425344 | elapsed time per iteration (s): 5.92 | learning rate: 5.163E-04 | global batch size: 512 | lm loss: 5.538472E+00 | loss scale: 8192.0 | grad norm: 0.287 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.484 | TFLOPs: 65.32 | +[default7]: iteration 545/ 3814 | consumed samples: 279040 | consumed tokens: 571473920 | elapsed time per iteration (s): 5.95 | learning rate: 5.162E-04 | global batch size: 512 | lm loss: 5.477728E+00 | loss scale: 8192.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.983 | TFLOPs: 64.94 | +[default7]: iteration 546/ 3814 | consumed samples: 279552 | consumed tokens: 572522496 | elapsed time per iteration (s): 5.91 | learning rate: 5.162E-04 | global batch size: 512 | lm loss: 5.491789E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.592 | TFLOPs: 65.40 | +[default7]: iteration 547/ 3814 | consumed samples: 280064 | consumed tokens: 573571072 | elapsed time per iteration (s): 5.95 | learning rate: 5.162E-04 | global batch size: 512 | lm loss: 5.511535E+00 | loss scale: 8192.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.054 | TFLOPs: 65.00 | +[default7]: iteration 548/ 3814 | consumed samples: 280576 | consumed tokens: 574619648 | elapsed time per iteration (s): 5.87 | learning rate: 5.161E-04 | global batch size: 512 | lm loss: 5.472215E+00 | loss scale: 8192.0 | grad norm: 0.285 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.294 | TFLOPs: 65.93 | +[default7]: iteration 549/ 3814 | consumed samples: 281088 | consumed tokens: 575668224 | elapsed time per iteration (s): 5.96 | learning rate: 5.161E-04 | global batch size: 512 | lm loss: 5.485523E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.961 | TFLOPs: 64.93 | +[default7]: iteration 550/ 3814 | consumed samples: 281600 | consumed tokens: 576716800 | elapsed time per iteration (s): 5.93 | learning rate: 5.160E-04 | global batch size: 512 | lm loss: 5.449271E+00 | loss scale: 8192.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.279 | TFLOPs: 65.17 | +[default7]: iteration 551/ 3814 | consumed samples: 282112 | consumed tokens: 577765376 | elapsed time per iteration (s): 5.93 | learning rate: 5.160E-04 | global batch size: 512 | lm loss: 5.467222E+00 | loss scale: 8192.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.299 | TFLOPs: 65.18 | +[default7]: iteration 552/ 3814 | consumed samples: 282624 | consumed tokens: 578813952 | elapsed time per iteration (s): 5.98 | learning rate: 5.160E-04 | global batch size: 512 | lm loss: 5.427932E+00 | loss scale: 8192.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 553/ 3814 | consumed samples: 283136 | consumed tokens: 579862528 | elapsed time per iteration (s): 5.96 | learning rate: 5.159E-04 | global batch size: 512 | lm loss: 5.464200E+00 | loss scale: 8192.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.941 | TFLOPs: 64.91 | +[default7]: iteration 554/ 3814 | consumed samples: 283648 | consumed tokens: 580911104 | elapsed time per iteration (s): 6.05 | learning rate: 5.159E-04 | global batch size: 512 | lm loss: 5.441618E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.666 | TFLOPs: 63.95 | +[default7]: iteration 555/ 3814 | consumed samples: 284160 | consumed tokens: 581959680 | elapsed time per iteration (s): 6.13 | learning rate: 5.158E-04 | global batch size: 512 | lm loss: 5.416081E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.532 | TFLOPs: 63.09 | +[default7]: iteration 556/ 3814 | consumed samples: 284672 | consumed tokens: 583008256 | elapsed time per iteration (s): 6.01 | learning rate: 5.158E-04 | global batch size: 512 | lm loss: 5.443484E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.137 | TFLOPs: 64.30 | +[default7]: iteration 557/ 3814 | consumed samples: 285184 | consumed tokens: 584056832 | elapsed time per iteration (s): 6.11 | learning rate: 5.157E-04 | global batch size: 512 | lm loss: 5.441331E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.732 | TFLOPs: 63.24 | +[default7]: iteration 558/ 3814 | consumed samples: 285696 | consumed tokens: 585105408 | elapsed time per iteration (s): 6.09 | learning rate: 5.157E-04 | global batch size: 512 | lm loss: 5.476543E+00 | loss scale: 8192.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.022 | TFLOPs: 63.46 | +[default7]: iteration 559/ 3814 | consumed samples: 286208 | consumed tokens: 586153984 | elapsed time per iteration (s): 6.15 | learning rate: 5.157E-04 | global batch size: 512 | lm loss: 5.450986E+00 | loss scale: 8192.0 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.275 | TFLOPs: 62.90 | +[default7]: iteration 560/ 3814 | consumed samples: 286720 | consumed tokens: 587202560 | elapsed time per iteration (s): 6.12 | learning rate: 5.156E-04 | global batch size: 512 | lm loss: 5.420608E+00 | loss scale: 8192.0 | grad norm: 0.284 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.661 | TFLOPs: 63.19 | +[default7]: iteration 561/ 3814 | consumed samples: 287232 | consumed tokens: 588251136 | elapsed time per iteration (s): 6.12 | learning rate: 5.156E-04 | global batch size: 512 | lm loss: 5.451232E+00 | loss scale: 8192.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.660 | TFLOPs: 63.19 | +[default7]: iteration 562/ 3814 | consumed samples: 287744 | consumed tokens: 589299712 | elapsed time per iteration (s): 6.18 | learning rate: 5.155E-04 | global batch size: 512 | lm loss: 5.440920E+00 | loss scale: 8192.0 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.816 | TFLOPs: 62.55 | +[default7]: iteration 563/ 3814 | consumed samples: 288256 | consumed tokens: 590348288 | elapsed time per iteration (s): 5.93 | learning rate: 5.155E-04 | global batch size: 512 | lm loss: 5.422479E+00 | loss scale: 8192.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.291 | TFLOPs: 65.18 | +[default7]: iteration 564/ 3814 | consumed samples: 288768 | consumed tokens: 591396864 | elapsed time per iteration (s): 5.93 | learning rate: 5.154E-04 | global batch size: 512 | lm loss: 5.428557E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.277 | TFLOPs: 65.17 | +[default7]: iteration 565/ 3814 | consumed samples: 289280 | consumed tokens: 592445440 | elapsed time per iteration (s): 5.94 | learning rate: 5.154E-04 | global batch size: 512 | lm loss: 5.421315E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.244 | TFLOPs: 65.14 | +[default7]: iteration 566/ 3814 | consumed samples: 289792 | consumed tokens: 593494016 | elapsed time per iteration (s): 5.93 | learning rate: 5.154E-04 | global batch size: 512 | lm loss: 5.404539E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.365 | TFLOPs: 65.23 | +[default7]: iteration 567/ 3814 | consumed samples: 290304 | consumed tokens: 594542592 | elapsed time per iteration (s): 5.98 | learning rate: 5.153E-04 | global batch size: 512 | lm loss: 5.370506E+00 | loss scale: 8192.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.623 | TFLOPs: 64.67 | +[default7]: iteration 568/ 3814 | consumed samples: 290816 | consumed tokens: 595591168 | elapsed time per iteration (s): 6.02 | learning rate: 5.153E-04 | global batch size: 512 | lm loss: 5.371906E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.993 | TFLOPs: 64.20 | +[default7]: iteration 569/ 3814 | consumed samples: 291328 | consumed tokens: 596639744 | elapsed time per iteration (s): 5.97 | learning rate: 5.152E-04 | global batch size: 512 | lm loss: 5.385880E+00 | loss scale: 8192.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.724 | TFLOPs: 64.75 | +[default7]: iteration 570/ 3814 | consumed samples: 291840 | consumed tokens: 597688320 | elapsed time per iteration (s): 6.01 | learning rate: 5.152E-04 | global batch size: 512 | lm loss: 5.395114E+00 | loss scale: 8192.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.209 | TFLOPs: 64.36 | +[default7]: iteration 571/ 3814 | consumed samples: 292352 | consumed tokens: 598736896 | elapsed time per iteration (s): 5.96 | learning rate: 5.151E-04 | global batch size: 512 | lm loss: 5.397498E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.908 | TFLOPs: 64.89 | +[default7]: iteration 572/ 3814 | consumed samples: 292864 | consumed tokens: 599785472 | elapsed time per iteration (s): 5.97 | learning rate: 5.151E-04 | global batch size: 512 | lm loss: 5.386738E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.735 | TFLOPs: 64.76 | +[default7]: iteration 573/ 3814 | consumed samples: 293376 | consumed tokens: 600834048 | elapsed time per iteration (s): 5.90 | learning rate: 5.150E-04 | global batch size: 512 | lm loss: 5.369621E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.806 | TFLOPs: 65.57 | +[default7]: iteration 574/ 3814 | consumed samples: 293888 | consumed tokens: 601882624 | elapsed time per iteration (s): 5.96 | learning rate: 5.150E-04 | global batch size: 512 | lm loss: 5.398513E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.911 | TFLOPs: 64.89 | +[default7]: iteration 575/ 3814 | consumed samples: 294400 | consumed tokens: 602931200 | elapsed time per iteration (s): 5.98 | learning rate: 5.149E-04 | global batch size: 512 | lm loss: 5.382483E+00 | loss scale: 8192.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.565 | TFLOPs: 64.63 | +[default7]: iteration 576/ 3814 | consumed samples: 294912 | consumed tokens: 603979776 | elapsed time per iteration (s): 5.93 | learning rate: 5.149E-04 | global batch size: 512 | lm loss: 5.396391E+00 | loss scale: 8192.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.346 | TFLOPs: 65.22 | +[default7]: iteration 577/ 3814 | consumed samples: 295424 | consumed tokens: 605028352 | elapsed time per iteration (s): 5.98 | learning rate: 5.149E-04 | global batch size: 512 | lm loss: 5.373453E+00 | loss scale: 8192.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.564 | TFLOPs: 64.63 | +[default7]: iteration 578/ 3814 | consumed samples: 295936 | consumed tokens: 606076928 | elapsed time per iteration (s): 5.95 | learning rate: 5.148E-04 | global batch size: 512 | lm loss: 5.405595E+00 | loss scale: 8192.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.108 | TFLOPs: 65.04 | +[default7]: iteration 579/ 3814 | consumed samples: 296448 | consumed tokens: 607125504 | elapsed time per iteration (s): 5.92 | learning rate: 5.148E-04 | global batch size: 512 | lm loss: 5.379654E+00 | loss scale: 8192.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.452 | TFLOPs: 65.30 | +[default7]: iteration 580/ 3814 | consumed samples: 296960 | consumed tokens: 608174080 | elapsed time per iteration (s): 5.94 | learning rate: 5.147E-04 | global batch size: 512 | lm loss: 5.365237E+00 | loss scale: 8192.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.182 | TFLOPs: 65.09 | +[default7]: iteration 581/ 3814 | consumed samples: 297472 | consumed tokens: 609222656 | elapsed time per iteration (s): 6.26 | learning rate: 5.147E-04 | global batch size: 512 | lm loss: 5.365837E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.841 | TFLOPs: 61.82 | +[default7]: iteration 582/ 3814 | consumed samples: 297984 | consumed tokens: 610271232 | elapsed time per iteration (s): 6.01 | learning rate: 5.146E-04 | global batch size: 512 | lm loss: 5.384964E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.186 | TFLOPs: 64.34 | +[default7]: iteration 583/ 3814 | consumed samples: 298496 | consumed tokens: 611319808 | elapsed time per iteration (s): 5.95 | learning rate: 5.146E-04 | global batch size: 512 | lm loss: 5.352101E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.065 | TFLOPs: 65.01 | +[default7]: iteration 584/ 3814 | consumed samples: 299008 | consumed tokens: 612368384 | elapsed time per iteration (s): 5.93 | learning rate: 5.145E-04 | global batch size: 512 | lm loss: 5.351912E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.339 | TFLOPs: 65.21 | +[default7]: iteration 585/ 3814 | consumed samples: 299520 | consumed tokens: 613416960 | elapsed time per iteration (s): 5.95 | learning rate: 5.145E-04 | global batch size: 512 | lm loss: 5.367199E+00 | loss scale: 8192.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.031 | TFLOPs: 64.98 | +[default7]: iteration 586/ 3814 | consumed samples: 300032 | consumed tokens: 614465536 | elapsed time per iteration (s): 5.96 | learning rate: 5.144E-04 | global batch size: 512 | lm loss: 5.367314E+00 | loss scale: 8192.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.971 | TFLOPs: 64.93 | +[default7]: iteration 587/ 3814 | consumed samples: 300544 | consumed tokens: 615514112 | elapsed time per iteration (s): 5.94 | learning rate: 5.144E-04 | global batch size: 512 | lm loss: 5.353111E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.155 | TFLOPs: 65.07 | +[default7]: iteration 588/ 3814 | consumed samples: 301056 | consumed tokens: 616562688 | elapsed time per iteration (s): 5.97 | learning rate: 5.143E-04 | global batch size: 512 | lm loss: 5.359285E+00 | loss scale: 8192.0 | grad norm: 0.295 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.791 | TFLOPs: 64.80 | +[default7]: iteration 589/ 3814 | consumed samples: 301568 | consumed tokens: 617611264 | elapsed time per iteration (s): 5.95 | learning rate: 5.143E-04 | global batch size: 512 | lm loss: 5.358411E+00 | loss scale: 8192.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.106 | TFLOPs: 65.04 | +[default7]: iteration 590/ 3814 | consumed samples: 302080 | consumed tokens: 618659840 | elapsed time per iteration (s): 5.99 | learning rate: 5.142E-04 | global batch size: 512 | lm loss: 5.302241E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.455 | TFLOPs: 64.55 | +[default7]: iteration 591/ 3814 | consumed samples: 302592 | consumed tokens: 619708416 | elapsed time per iteration (s): 5.97 | learning rate: 5.142E-04 | global batch size: 512 | lm loss: 5.353131E+00 | loss scale: 8192.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.831 | TFLOPs: 64.83 | +[default7]: iteration 592/ 3814 | consumed samples: 303104 | consumed tokens: 620756992 | elapsed time per iteration (s): 5.89 | learning rate: 5.141E-04 | global batch size: 512 | lm loss: 5.317591E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.920 | TFLOPs: 65.65 | +[default7]: iteration 593/ 3814 | consumed samples: 303616 | consumed tokens: 621805568 | elapsed time per iteration (s): 5.97 | learning rate: 5.141E-04 | global batch size: 512 | lm loss: 5.316384E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.807 | TFLOPs: 64.81 | +[default7]: iteration 594/ 3814 | consumed samples: 304128 | consumed tokens: 622854144 | elapsed time per iteration (s): 5.97 | learning rate: 5.140E-04 | global batch size: 512 | lm loss: 5.329311E+00 | loss scale: 8192.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.796 | TFLOPs: 64.80 | +[default7]: iteration 595/ 3814 | consumed samples: 304640 | consumed tokens: 623902720 | elapsed time per iteration (s): 5.96 | learning rate: 5.140E-04 | global batch size: 512 | lm loss: 5.330329E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.851 | TFLOPs: 64.84 | +[default7]: iteration 596/ 3814 | consumed samples: 305152 | consumed tokens: 624951296 | elapsed time per iteration (s): 6.02 | learning rate: 5.139E-04 | global batch size: 512 | lm loss: 5.311607E+00 | loss scale: 8192.0 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.032 | TFLOPs: 64.23 | +[default7]: iteration 597/ 3814 | consumed samples: 305664 | consumed tokens: 625999872 | elapsed time per iteration (s): 6.04 | learning rate: 5.139E-04 | global batch size: 512 | lm loss: 5.327603E+00 | loss scale: 8192.0 | grad norm: 0.312 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.796 | TFLOPs: 64.05 | +[default7]: iteration 598/ 3814 | consumed samples: 306176 | consumed tokens: 627048448 | elapsed time per iteration (s): 5.93 | learning rate: 5.138E-04 | global batch size: 512 | lm loss: 5.319065E+00 | loss scale: 8192.0 | grad norm: 0.313 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.384 | TFLOPs: 65.25 | +[default7]: iteration 599/ 3814 | consumed samples: 306688 | consumed tokens: 628097024 | elapsed time per iteration (s): 6.00 | learning rate: 5.138E-04 | global batch size: 512 | lm loss: 5.323179E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.307 | TFLOPs: 64.43 | +[default7]: iteration 600/ 3814 | consumed samples: 307200 | consumed tokens: 629145600 | elapsed time per iteration (s): 5.95 | learning rate: 5.137E-04 | global batch size: 512 | lm loss: 5.312118E+00 | loss scale: 8192.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.021 | TFLOPs: 64.97 | +[default7]: iteration 601/ 3814 | consumed samples: 307712 | consumed tokens: 630194176 | elapsed time per iteration (s): 5.99 | learning rate: 5.137E-04 | global batch size: 512 | lm loss: 5.334136E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.437 | TFLOPs: 64.53 | +[default7]: iteration 602/ 3814 | consumed samples: 308224 | consumed tokens: 631242752 | elapsed time per iteration (s): 5.88 | learning rate: 5.136E-04 | global batch size: 512 | lm loss: 5.315865E+00 | loss scale: 8192.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.144 | TFLOPs: 65.82 | +[default7]: iteration 603/ 3814 | consumed samples: 308736 | consumed tokens: 632291328 | elapsed time per iteration (s): 6.01 | learning rate: 5.136E-04 | global batch size: 512 | lm loss: 5.304075E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.205 | TFLOPs: 64.36 | +[default7]: iteration 604/ 3814 | consumed samples: 309248 | consumed tokens: 633339904 | elapsed time per iteration (s): 5.87 | learning rate: 5.135E-04 | global batch size: 512 | lm loss: 5.309111E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.176 | TFLOPs: 65.85 | +[default7]: iteration 605/ 3814 | consumed samples: 309760 | consumed tokens: 634388480 | elapsed time per iteration (s): 5.96 | learning rate: 5.135E-04 | global batch size: 512 | lm loss: 5.271771E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.932 | TFLOPs: 64.91 | +[default7]: iteration 606/ 3814 | consumed samples: 310272 | consumed tokens: 635437056 | elapsed time per iteration (s): 5.98 | learning rate: 5.134E-04 | global batch size: 512 | lm loss: 5.286836E+00 | loss scale: 8192.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.652 | TFLOPs: 64.69 | +[default7]: iteration 607/ 3814 | consumed samples: 310784 | consumed tokens: 636485632 | elapsed time per iteration (s): 5.84 | learning rate: 5.134E-04 | global batch size: 512 | lm loss: 5.254997E+00 | loss scale: 8192.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.683 | TFLOPs: 66.23 | +[default7]: iteration 608/ 3814 | consumed samples: 311296 | consumed tokens: 637534208 | elapsed time per iteration (s): 5.94 | learning rate: 5.133E-04 | global batch size: 512 | lm loss: 5.234874E+00 | loss scale: 8192.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.201 | TFLOPs: 65.11 | +[default7]: iteration 609/ 3814 | consumed samples: 311808 | consumed tokens: 638582784 | elapsed time per iteration (s): 5.98 | learning rate: 5.132E-04 | global batch size: 512 | lm loss: 5.288463E+00 | loss scale: 8192.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.644 | TFLOPs: 64.69 | +[default7]: iteration 610/ 3814 | consumed samples: 312320 | consumed tokens: 639631360 | elapsed time per iteration (s): 5.97 | learning rate: 5.132E-04 | global batch size: 512 | lm loss: 5.267952E+00 | loss scale: 8192.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.757 | TFLOPs: 64.77 | +[default7]: iteration 611/ 3814 | consumed samples: 312832 | consumed tokens: 640679936 | elapsed time per iteration (s): 5.98 | learning rate: 5.131E-04 | global batch size: 512 | lm loss: 5.265638E+00 | loss scale: 8192.0 | grad norm: 0.244 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 612/ 3814 | consumed samples: 313344 | consumed tokens: 641728512 | elapsed time per iteration (s): 6.01 | learning rate: 5.131E-04 | global batch size: 512 | lm loss: 5.292151E+00 | loss scale: 8192.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.208 | TFLOPs: 64.36 | +[default7]: iteration 613/ 3814 | consumed samples: 313856 | consumed tokens: 642777088 | elapsed time per iteration (s): 5.92 | learning rate: 5.130E-04 | global batch size: 512 | lm loss: 5.261147E+00 | loss scale: 8192.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.520 | TFLOPs: 65.35 | +[default7]: iteration 614/ 3814 | consumed samples: 314368 | consumed tokens: 643825664 | elapsed time per iteration (s): 5.94 | learning rate: 5.130E-04 | global batch size: 512 | lm loss: 5.288074E+00 | loss scale: 8192.0 | grad norm: 0.362 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.203 | TFLOPs: 65.11 | +[default7]: iteration 615/ 3814 | consumed samples: 314880 | consumed tokens: 644874240 | elapsed time per iteration (s): 5.97 | learning rate: 5.129E-04 | global batch size: 512 | lm loss: 5.273936E+00 | loss scale: 8192.0 | grad norm: 0.319 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.755 | TFLOPs: 64.77 | +[default7]: iteration 616/ 3814 | consumed samples: 315392 | consumed tokens: 645922816 | elapsed time per iteration (s): 5.90 | learning rate: 5.129E-04 | global batch size: 512 | lm loss: 5.289597E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.715 | TFLOPs: 65.50 | +[default7]: iteration 617/ 3814 | consumed samples: 315904 | consumed tokens: 646971392 | elapsed time per iteration (s): 5.95 | learning rate: 5.128E-04 | global batch size: 512 | lm loss: 5.255388E+00 | loss scale: 8192.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.052 | TFLOPs: 65.00 | +[default7]: iteration 618/ 3814 | consumed samples: 316416 | consumed tokens: 648019968 | elapsed time per iteration (s): 5.92 | learning rate: 5.128E-04 | global batch size: 512 | lm loss: 5.265219E+00 | loss scale: 8192.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.525 | TFLOPs: 65.35 | +[default7]: iteration 619/ 3814 | consumed samples: 316928 | consumed tokens: 649068544 | elapsed time per iteration (s): 5.94 | learning rate: 5.127E-04 | global batch size: 512 | lm loss: 5.246308E+00 | loss scale: 8192.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.123 | TFLOPs: 65.05 | +[default7]: iteration 620/ 3814 | consumed samples: 317440 | consumed tokens: 650117120 | elapsed time per iteration (s): 5.97 | learning rate: 5.126E-04 | global batch size: 512 | lm loss: 5.232125E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.796 | TFLOPs: 64.80 | +[default7]: iteration 621/ 3814 | consumed samples: 317952 | consumed tokens: 651165696 | elapsed time per iteration (s): 5.97 | learning rate: 5.126E-04 | global batch size: 512 | lm loss: 5.225776E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.816 | TFLOPs: 64.82 | +[default7]: iteration 622/ 3814 | consumed samples: 318464 | consumed tokens: 652214272 | elapsed time per iteration (s): 5.96 | learning rate: 5.125E-04 | global batch size: 512 | lm loss: 5.247089E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.971 | TFLOPs: 64.94 | +[default7]: iteration 623/ 3814 | consumed samples: 318976 | consumed tokens: 653262848 | elapsed time per iteration (s): 5.94 | learning rate: 5.125E-04 | global batch size: 512 | lm loss: 5.227985E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.208 | TFLOPs: 65.11 | +[default7]: iteration 624/ 3814 | consumed samples: 319488 | consumed tokens: 654311424 | elapsed time per iteration (s): 5.93 | learning rate: 5.124E-04 | global batch size: 512 | lm loss: 5.194085E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.332 | TFLOPs: 65.21 | +[default7]: iteration 625/ 3814 | consumed samples: 320000 | consumed tokens: 655360000 | elapsed time per iteration (s): 5.95 | learning rate: 5.124E-04 | global batch size: 512 | lm loss: 5.247315E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.093 | TFLOPs: 65.03 | +[default7]: iteration 626/ 3814 | consumed samples: 320512 | consumed tokens: 656408576 | elapsed time per iteration (s): 6.00 | learning rate: 5.123E-04 | global batch size: 512 | lm loss: 5.207446E+00 | loss scale: 8192.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.365 | TFLOPs: 64.48 | +[default7]: iteration 627/ 3814 | consumed samples: 321024 | consumed tokens: 657457152 | elapsed time per iteration (s): 5.98 | learning rate: 5.122E-04 | global batch size: 512 | lm loss: 5.208412E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.564 | TFLOPs: 64.63 | +[default7]: iteration 628/ 3814 | consumed samples: 321536 | consumed tokens: 658505728 | elapsed time per iteration (s): 5.85 | learning rate: 5.122E-04 | global batch size: 512 | lm loss: 5.184804E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.566 | TFLOPs: 66.14 | +[default7]: iteration 629/ 3814 | consumed samples: 322048 | consumed tokens: 659554304 | elapsed time per iteration (s): 6.04 | learning rate: 5.121E-04 | global batch size: 512 | lm loss: 5.203656E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.817 | TFLOPs: 64.06 | +[default7]: iteration 630/ 3814 | consumed samples: 322560 | consumed tokens: 660602880 | elapsed time per iteration (s): 5.98 | learning rate: 5.121E-04 | global batch size: 512 | lm loss: 5.184941E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.626 | TFLOPs: 64.67 | +[default7]: iteration 631/ 3814 | consumed samples: 323072 | consumed tokens: 661651456 | elapsed time per iteration (s): 5.93 | learning rate: 5.120E-04 | global batch size: 512 | lm loss: 5.208861E+00 | loss scale: 8192.0 | grad norm: 0.250 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.304 | TFLOPs: 65.19 | +[default7]: iteration 632/ 3814 | consumed samples: 323584 | consumed tokens: 662700032 | elapsed time per iteration (s): 5.96 | learning rate: 5.120E-04 | global batch size: 512 | lm loss: 5.194866E+00 | loss scale: 8192.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.973 | TFLOPs: 64.94 | +[default7]: iteration 633/ 3814 | consumed samples: 324096 | consumed tokens: 663748608 | elapsed time per iteration (s): 5.92 | learning rate: 5.119E-04 | global batch size: 512 | lm loss: 5.217874E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.422 | TFLOPs: 65.28 | +[default7]: iteration 634/ 3814 | consumed samples: 324608 | consumed tokens: 664797184 | elapsed time per iteration (s): 5.97 | learning rate: 5.118E-04 | global batch size: 512 | lm loss: 5.217872E+00 | loss scale: 8192.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.775 | TFLOPs: 64.79 | +[default7]: iteration 635/ 3814 | consumed samples: 325120 | consumed tokens: 665845760 | elapsed time per iteration (s): 5.94 | learning rate: 5.118E-04 | global batch size: 512 | lm loss: 5.201051E+00 | loss scale: 8192.0 | grad norm: 0.303 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.262 | TFLOPs: 65.15 | +[default7]: iteration 636/ 3814 | consumed samples: 325632 | consumed tokens: 666894336 | elapsed time per iteration (s): 5.96 | learning rate: 5.117E-04 | global batch size: 512 | lm loss: 5.255648E+00 | loss scale: 8192.0 | grad norm: 0.393 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.973 | TFLOPs: 64.94 | +[default7]: iteration 637/ 3814 | consumed samples: 326144 | consumed tokens: 667942912 | elapsed time per iteration (s): 5.97 | learning rate: 5.117E-04 | global batch size: 512 | lm loss: 5.207139E+00 | loss scale: 8192.0 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.812 | TFLOPs: 64.81 | +[default7]: iteration 638/ 3814 | consumed samples: 326656 | consumed tokens: 668991488 | elapsed time per iteration (s): 6.00 | learning rate: 5.116E-04 | global batch size: 512 | lm loss: 5.233207E+00 | loss scale: 8192.0 | grad norm: 0.352 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.281 | TFLOPs: 64.41 | +[default7]: iteration 639/ 3814 | consumed samples: 327168 | consumed tokens: 670040064 | elapsed time per iteration (s): 5.98 | learning rate: 5.115E-04 | global batch size: 512 | lm loss: 5.202569E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.596 | TFLOPs: 64.65 | +[default7]: iteration 640/ 3814 | consumed samples: 327680 | consumed tokens: 671088640 | elapsed time per iteration (s): 5.94 | learning rate: 5.115E-04 | global batch size: 512 | lm loss: 5.188194E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.202 | TFLOPs: 65.11 | +[default7]: iteration 641/ 3814 | consumed samples: 328192 | consumed tokens: 672137216 | elapsed time per iteration (s): 6.02 | learning rate: 5.114E-04 | global batch size: 512 | lm loss: 5.196885E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.101 | TFLOPs: 64.28 | +[default7]: iteration 642/ 3814 | consumed samples: 328704 | consumed tokens: 673185792 | elapsed time per iteration (s): 5.97 | learning rate: 5.114E-04 | global batch size: 512 | lm loss: 5.189776E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.721 | TFLOPs: 64.75 | +[default7]: iteration 643/ 3814 | consumed samples: 329216 | consumed tokens: 674234368 | elapsed time per iteration (s): 5.95 | learning rate: 5.113E-04 | global batch size: 512 | lm loss: 5.205935E+00 | loss scale: 8192.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.015 | TFLOPs: 64.97 | +[default7]: iteration 644/ 3814 | consumed samples: 329728 | consumed tokens: 675282944 | elapsed time per iteration (s): 6.01 | learning rate: 5.112E-04 | global batch size: 512 | lm loss: 5.163267E+00 | loss scale: 8192.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.154 | TFLOPs: 64.32 | +[default7]: iteration 645/ 3814 | consumed samples: 330240 | consumed tokens: 676331520 | elapsed time per iteration (s): 6.02 | learning rate: 5.112E-04 | global batch size: 512 | lm loss: 5.160785E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.063 | TFLOPs: 64.25 | +[default7]: iteration 646/ 3814 | consumed samples: 330752 | consumed tokens: 677380096 | elapsed time per iteration (s): 5.92 | learning rate: 5.111E-04 | global batch size: 512 | lm loss: 5.165056E+00 | loss scale: 8192.0 | grad norm: 0.236 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.529 | TFLOPs: 65.36 | +[default7]: iteration 647/ 3814 | consumed samples: 331264 | consumed tokens: 678428672 | elapsed time per iteration (s): 5.92 | learning rate: 5.111E-04 | global batch size: 512 | lm loss: 5.148671E+00 | loss scale: 8192.0 | grad norm: 0.249 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.494 | TFLOPs: 65.33 | +[default7]: iteration 648/ 3814 | consumed samples: 331776 | consumed tokens: 679477248 | elapsed time per iteration (s): 6.05 | learning rate: 5.110E-04 | global batch size: 512 | lm loss: 5.162131E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.640 | TFLOPs: 63.93 | +[default7]: iteration 649/ 3814 | consumed samples: 332288 | consumed tokens: 680525824 | elapsed time per iteration (s): 5.96 | learning rate: 5.109E-04 | global batch size: 512 | lm loss: 5.143456E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.977 | TFLOPs: 64.94 | +[default7]: iteration 650/ 3814 | consumed samples: 332800 | consumed tokens: 681574400 | elapsed time per iteration (s): 5.88 | learning rate: 5.109E-04 | global batch size: 512 | lm loss: 5.165577E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.056 | TFLOPs: 65.75 | +[default7]: iteration 651/ 3814 | consumed samples: 333312 | consumed tokens: 682622976 | elapsed time per iteration (s): 5.95 | learning rate: 5.108E-04 | global batch size: 512 | lm loss: 5.123676E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.013 | TFLOPs: 64.97 | +[default7]: iteration 652/ 3814 | consumed samples: 333824 | consumed tokens: 683671552 | elapsed time per iteration (s): 5.97 | learning rate: 5.108E-04 | global batch size: 512 | lm loss: 5.176905E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.698 | TFLOPs: 64.73 | +[default7]: iteration 653/ 3814 | consumed samples: 334336 | consumed tokens: 684720128 | elapsed time per iteration (s): 5.95 | learning rate: 5.107E-04 | global batch size: 512 | lm loss: 5.149479E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.985 | TFLOPs: 64.95 | +[default7]: iteration 654/ 3814 | consumed samples: 334848 | consumed tokens: 685768704 | elapsed time per iteration (s): 6.08 | learning rate: 5.106E-04 | global batch size: 512 | lm loss: 5.143127E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.206 | TFLOPs: 63.60 | +[default7]: iteration 655/ 3814 | consumed samples: 335360 | consumed tokens: 686817280 | elapsed time per iteration (s): 6.03 | learning rate: 5.106E-04 | global batch size: 512 | lm loss: 5.126942E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.904 | TFLOPs: 64.13 | +[default7]: iteration 656/ 3814 | consumed samples: 335872 | consumed tokens: 687865856 | elapsed time per iteration (s): 5.96 | learning rate: 5.105E-04 | global batch size: 512 | lm loss: 5.090899E+00 | loss scale: 8192.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.857 | TFLOPs: 64.85 | +[default7]: iteration 657/ 3814 | consumed samples: 336384 | consumed tokens: 688914432 | elapsed time per iteration (s): 6.00 | learning rate: 5.104E-04 | global batch size: 512 | lm loss: 5.141289E+00 | loss scale: 8192.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.364 | TFLOPs: 64.48 | +[default7]: iteration 658/ 3814 | consumed samples: 336896 | consumed tokens: 689963008 | elapsed time per iteration (s): 5.95 | learning rate: 5.104E-04 | global batch size: 512 | lm loss: 5.129676E+00 | loss scale: 8192.0 | grad norm: 0.306 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.050 | TFLOPs: 64.99 | +[default7]: iteration 659/ 3814 | consumed samples: 337408 | consumed tokens: 691011584 | elapsed time per iteration (s): 6.01 | learning rate: 5.103E-04 | global batch size: 512 | lm loss: 5.103197E+00 | loss scale: 8192.0 | grad norm: 0.360 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.137 | TFLOPs: 64.31 | +[default7]: iteration 660/ 3814 | consumed samples: 337920 | consumed tokens: 692060160 | elapsed time per iteration (s): 5.96 | learning rate: 5.102E-04 | global batch size: 512 | lm loss: 5.108667E+00 | loss scale: 8192.0 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.839 | TFLOPs: 64.84 | +[default7]: iteration 661/ 3814 | consumed samples: 338432 | consumed tokens: 693108736 | elapsed time per iteration (s): 5.93 | learning rate: 5.102E-04 | global batch size: 512 | lm loss: 5.127185E+00 | loss scale: 8192.0 | grad norm: 0.280 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.327 | TFLOPs: 65.20 | +[default7]: iteration 662/ 3814 | consumed samples: 338944 | consumed tokens: 694157312 | elapsed time per iteration (s): 5.95 | learning rate: 5.101E-04 | global batch size: 512 | lm loss: 5.141832E+00 | loss scale: 8192.0 | grad norm: 0.316 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.011 | TFLOPs: 64.96 | +[default7]: iteration 663/ 3814 | consumed samples: 339456 | consumed tokens: 695205888 | elapsed time per iteration (s): 5.95 | learning rate: 5.101E-04 | global batch size: 512 | lm loss: 5.139823E+00 | loss scale: 8192.0 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.001 | TFLOPs: 64.96 | +[default7]: iteration 664/ 3814 | consumed samples: 339968 | consumed tokens: 696254464 | elapsed time per iteration (s): 5.96 | learning rate: 5.100E-04 | global batch size: 512 | lm loss: 5.125113E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.918 | TFLOPs: 64.89 | +[default7]: iteration 665/ 3814 | consumed samples: 340480 | consumed tokens: 697303040 | elapsed time per iteration (s): 5.97 | learning rate: 5.099E-04 | global batch size: 512 | lm loss: 5.124143E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.722 | TFLOPs: 64.75 | +[default7]: iteration 666/ 3814 | consumed samples: 340992 | consumed tokens: 698351616 | elapsed time per iteration (s): 5.95 | learning rate: 5.099E-04 | global batch size: 512 | lm loss: 5.112736E+00 | loss scale: 8192.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.003 | TFLOPs: 64.96 | +[default7]: iteration 667/ 3814 | consumed samples: 341504 | consumed tokens: 699400192 | elapsed time per iteration (s): 5.99 | learning rate: 5.098E-04 | global batch size: 512 | lm loss: 5.099428E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.424 | TFLOPs: 64.52 | +[default7]: iteration 668/ 3814 | consumed samples: 342016 | consumed tokens: 700448768 | elapsed time per iteration (s): 6.01 | learning rate: 5.097E-04 | global batch size: 512 | lm loss: 5.067336E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.222 | TFLOPs: 64.37 | +[default7]: iteration 669/ 3814 | consumed samples: 342528 | consumed tokens: 701497344 | elapsed time per iteration (s): 5.91 | learning rate: 5.097E-04 | global batch size: 512 | lm loss: 5.090704E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.587 | TFLOPs: 65.40 | +[default7]: iteration 670/ 3814 | consumed samples: 343040 | consumed tokens: 702545920 | elapsed time per iteration (s): 5.98 | learning rate: 5.096E-04 | global batch size: 512 | lm loss: 5.071217E+00 | loss scale: 8192.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.594 | TFLOPs: 64.65 | +[default7]: iteration 671/ 3814 | consumed samples: 343552 | consumed tokens: 703594496 | elapsed time per iteration (s): 5.97 | learning rate: 5.095E-04 | global batch size: 512 | lm loss: 5.087130E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.794 | TFLOPs: 64.80 | +[default7]: iteration 672/ 3814 | consumed samples: 344064 | consumed tokens: 704643072 | elapsed time per iteration (s): 5.97 | learning rate: 5.095E-04 | global batch size: 512 | lm loss: 5.061768E+00 | loss scale: 8192.0 | grad norm: 0.279 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.702 | TFLOPs: 64.73 | +[default7]: iteration 673/ 3814 | consumed samples: 344576 | consumed tokens: 705691648 | elapsed time per iteration (s): 5.99 | learning rate: 5.094E-04 | global batch size: 512 | lm loss: 5.093855E+00 | loss scale: 8192.0 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.494 | TFLOPs: 64.57 | +[default7]: iteration 674/ 3814 | consumed samples: 345088 | consumed tokens: 706740224 | elapsed time per iteration (s): 5.97 | learning rate: 5.093E-04 | global batch size: 512 | lm loss: 5.058999E+00 | loss scale: 8192.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.829 | TFLOPs: 64.83 | +[default7]: iteration 675/ 3814 | consumed samples: 345600 | consumed tokens: 707788800 | elapsed time per iteration (s): 6.00 | learning rate: 5.093E-04 | global batch size: 512 | lm loss: 5.069438E+00 | loss scale: 8192.0 | grad norm: 0.255 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.284 | TFLOPs: 64.42 | +[default7]: iteration 676/ 3814 | consumed samples: 346112 | consumed tokens: 708837376 | elapsed time per iteration (s): 6.02 | learning rate: 5.092E-04 | global batch size: 512 | lm loss: 5.083799E+00 | loss scale: 8192.0 | grad norm: 0.228 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.007 | TFLOPs: 64.21 | +[default7]: iteration 677/ 3814 | consumed samples: 346624 | consumed tokens: 709885952 | elapsed time per iteration (s): 6.01 | learning rate: 5.091E-04 | global batch size: 512 | lm loss: 5.052477E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.123 | TFLOPs: 64.29 | +[default7]: iteration 678/ 3814 | consumed samples: 347136 | consumed tokens: 710934528 | elapsed time per iteration (s): 5.95 | learning rate: 5.091E-04 | global batch size: 512 | lm loss: 5.054995E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.031 | TFLOPs: 64.98 | +[default7]: iteration 679/ 3814 | consumed samples: 347648 | consumed tokens: 711983104 | elapsed time per iteration (s): 5.98 | learning rate: 5.090E-04 | global batch size: 512 | lm loss: 5.031333E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.660 | TFLOPs: 64.70 | +[default7]: iteration 680/ 3814 | consumed samples: 348160 | consumed tokens: 713031680 | elapsed time per iteration (s): 5.98 | learning rate: 5.089E-04 | global batch size: 512 | lm loss: 5.055780E+00 | loss scale: 8192.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.663 | TFLOPs: 64.70 | +[default7]: iteration 681/ 3814 | consumed samples: 348672 | consumed tokens: 714080256 | elapsed time per iteration (s): 5.97 | learning rate: 5.089E-04 | global batch size: 512 | lm loss: 5.059340E+00 | loss scale: 8192.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.696 | TFLOPs: 64.73 | +[default7]: iteration 682/ 3814 | consumed samples: 349184 | consumed tokens: 715128832 | elapsed time per iteration (s): 5.66 | learning rate: 5.088E-04 | global batch size: 512 | lm loss: 5.052003E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.493 | TFLOPs: 68.35 | +[default7]: iteration 683/ 3814 | consumed samples: 349696 | consumed tokens: 716177408 | elapsed time per iteration (s): 5.96 | learning rate: 5.087E-04 | global batch size: 512 | lm loss: 5.045779E+00 | loss scale: 8192.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.968 | TFLOPs: 64.93 | +[default7]: iteration 684/ 3814 | consumed samples: 350208 | consumed tokens: 717225984 | elapsed time per iteration (s): 5.92 | learning rate: 5.086E-04 | global batch size: 512 | lm loss: 5.025392E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.534 | TFLOPs: 65.36 | +[default7]: iteration 685/ 3814 | consumed samples: 350720 | consumed tokens: 718274560 | elapsed time per iteration (s): 5.97 | learning rate: 5.086E-04 | global batch size: 512 | lm loss: 5.046054E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.778 | TFLOPs: 64.79 | +[default7]: iteration 686/ 3814 | consumed samples: 351232 | consumed tokens: 719323136 | elapsed time per iteration (s): 5.88 | learning rate: 5.085E-04 | global batch size: 512 | lm loss: 5.010088E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.121 | TFLOPs: 65.80 | +[default7]: iteration 687/ 3814 | consumed samples: 351744 | consumed tokens: 720371712 | elapsed time per iteration (s): 5.93 | learning rate: 5.084E-04 | global batch size: 512 | lm loss: 5.024936E+00 | loss scale: 8192.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.362 | TFLOPs: 65.23 | +[default7]: iteration 688/ 3814 | consumed samples: 352256 | consumed tokens: 721420288 | elapsed time per iteration (s): 5.98 | learning rate: 5.084E-04 | global batch size: 512 | lm loss: 5.013252E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.661 | TFLOPs: 64.70 | +[default7]: iteration 689/ 3814 | consumed samples: 352768 | consumed tokens: 722468864 | elapsed time per iteration (s): 5.99 | learning rate: 5.083E-04 | global batch size: 512 | lm loss: 5.024395E+00 | loss scale: 8192.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.476 | TFLOPs: 64.56 | +[default7]: iteration 690/ 3814 | consumed samples: 353280 | consumed tokens: 723517440 | elapsed time per iteration (s): 6.02 | learning rate: 5.082E-04 | global batch size: 512 | lm loss: 5.015440E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.055 | TFLOPs: 64.24 | +[default7]: iteration 691/ 3814 | consumed samples: 353792 | consumed tokens: 724566016 | elapsed time per iteration (s): 6.06 | learning rate: 5.082E-04 | global batch size: 512 | lm loss: 5.003981E+00 | loss scale: 8192.0 | grad norm: 0.226 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.519 | TFLOPs: 63.84 | +[default7]: iteration 692/ 3814 | consumed samples: 354304 | consumed tokens: 725614592 | elapsed time per iteration (s): 5.90 | learning rate: 5.081E-04 | global batch size: 512 | lm loss: 5.002275E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.768 | TFLOPs: 65.54 | +[default7]: iteration 693/ 3814 | consumed samples: 354816 | consumed tokens: 726663168 | elapsed time per iteration (s): 5.99 | learning rate: 5.080E-04 | global batch size: 512 | lm loss: 4.992131E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.420 | TFLOPs: 64.52 | +[default7]: iteration 694/ 3814 | consumed samples: 355328 | consumed tokens: 727711744 | elapsed time per iteration (s): 6.01 | learning rate: 5.079E-04 | global batch size: 512 | lm loss: 4.975227E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.262 | TFLOPs: 64.40 | +[default7]: iteration 695/ 3814 | consumed samples: 355840 | consumed tokens: 728760320 | elapsed time per iteration (s): 5.94 | learning rate: 5.079E-04 | global batch size: 512 | lm loss: 4.999203E+00 | loss scale: 8192.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.209 | TFLOPs: 65.11 | +[default7]: iteration 696/ 3814 | consumed samples: 356352 | consumed tokens: 729808896 | elapsed time per iteration (s): 5.89 | learning rate: 5.078E-04 | global batch size: 512 | lm loss: 4.954316E+00 | loss scale: 8192.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.923 | TFLOPs: 65.65 | +[default7]: iteration 697/ 3814 | consumed samples: 356864 | consumed tokens: 730857472 | elapsed time per iteration (s): 5.99 | learning rate: 5.077E-04 | global batch size: 512 | lm loss: 4.978598E+00 | loss scale: 8192.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.522 | TFLOPs: 64.60 | +[default7]: iteration 698/ 3814 | consumed samples: 357376 | consumed tokens: 731906048 | elapsed time per iteration (s): 5.96 | learning rate: 5.077E-04 | global batch size: 512 | lm loss: 4.992190E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.856 | TFLOPs: 64.85 | +[default7]: iteration 699/ 3814 | consumed samples: 357888 | consumed tokens: 732954624 | elapsed time per iteration (s): 5.90 | learning rate: 5.076E-04 | global batch size: 512 | lm loss: 4.965649E+00 | loss scale: 8192.0 | grad norm: 0.353 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.750 | TFLOPs: 65.52 | +[default7]: iteration 700/ 3814 | consumed samples: 358400 | consumed tokens: 734003200 | elapsed time per iteration (s): 5.96 | learning rate: 5.075E-04 | global batch size: 512 | lm loss: 4.991684E+00 | loss scale: 8192.0 | grad norm: 0.339 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.949 | TFLOPs: 64.92 | +[default7]: iteration 701/ 3814 | consumed samples: 358912 | consumed tokens: 735051776 | elapsed time per iteration (s): 6.01 | learning rate: 5.074E-04 | global batch size: 512 | lm loss: 4.972850E+00 | loss scale: 8192.0 | grad norm: 0.327 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.162 | TFLOPs: 64.32 | +[default7]: iteration 702/ 3814 | consumed samples: 359424 | consumed tokens: 736100352 | elapsed time per iteration (s): 5.97 | learning rate: 5.074E-04 | global batch size: 512 | lm loss: 5.006995E+00 | loss scale: 8192.0 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.799 | TFLOPs: 64.80 | +[default7]: iteration 703/ 3814 | consumed samples: 359936 | consumed tokens: 737148928 | elapsed time per iteration (s): 5.98 | learning rate: 5.073E-04 | global batch size: 512 | lm loss: 4.978950E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.550 | TFLOPs: 64.62 | +[default7]: iteration 704/ 3814 | consumed samples: 360448 | consumed tokens: 738197504 | elapsed time per iteration (s): 6.04 | learning rate: 5.072E-04 | global batch size: 512 | lm loss: 4.973362E+00 | loss scale: 8192.0 | grad norm: 0.218 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.816 | TFLOPs: 64.06 | +[default7]: iteration 705/ 3814 | consumed samples: 360960 | consumed tokens: 739246080 | elapsed time per iteration (s): 5.95 | learning rate: 5.072E-04 | global batch size: 512 | lm loss: 4.959147E+00 | loss scale: 8192.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.012 | TFLOPs: 64.97 | +[default7]: iteration 706/ 3814 | consumed samples: 361472 | consumed tokens: 740294656 | elapsed time per iteration (s): 5.95 | learning rate: 5.071E-04 | global batch size: 512 | lm loss: 4.976042E+00 | loss scale: 8192.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.014 | TFLOPs: 64.97 | +[default7]: iteration 707/ 3814 | consumed samples: 361984 | consumed tokens: 741343232 | elapsed time per iteration (s): 5.99 | learning rate: 5.070E-04 | global batch size: 512 | lm loss: 4.952471E+00 | loss scale: 8192.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.529 | TFLOPs: 64.60 | +[default7]: iteration 708/ 3814 | consumed samples: 362496 | consumed tokens: 742391808 | elapsed time per iteration (s): 5.67 | learning rate: 5.069E-04 | global batch size: 512 | lm loss: 4.944058E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.342 | TFLOPs: 68.24 | +[default7]: iteration 709/ 3814 | consumed samples: 363008 | consumed tokens: 743440384 | elapsed time per iteration (s): 5.99 | learning rate: 5.069E-04 | global batch size: 512 | lm loss: 4.941481E+00 | loss scale: 8192.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.449 | TFLOPs: 64.54 | +[default7]: iteration 710/ 3814 | consumed samples: 363520 | consumed tokens: 744488960 | elapsed time per iteration (s): 6.00 | learning rate: 5.068E-04 | global batch size: 512 | lm loss: 4.936099E+00 | loss scale: 8192.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 711/ 3814 | consumed samples: 364032 | consumed tokens: 745537536 | elapsed time per iteration (s): 6.00 | learning rate: 5.067E-04 | global batch size: 512 | lm loss: 4.941858E+00 | loss scale: 8192.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.366 | TFLOPs: 64.48 | +[default7]: iteration 712/ 3814 | consumed samples: 364544 | consumed tokens: 746586112 | elapsed time per iteration (s): 5.66 | learning rate: 5.066E-04 | global batch size: 512 | lm loss: 4.921757E+00 | loss scale: 8192.0 | grad norm: 0.257 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.440 | TFLOPs: 68.31 | +[default7]: iteration 713/ 3814 | consumed samples: 365056 | consumed tokens: 747634688 | elapsed time per iteration (s): 5.98 | learning rate: 5.066E-04 | global batch size: 512 | lm loss: 4.931320E+00 | loss scale: 8192.0 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.587 | TFLOPs: 64.64 | +[default7]: iteration 714/ 3814 | consumed samples: 365568 | consumed tokens: 748683264 | elapsed time per iteration (s): 5.98 | learning rate: 5.065E-04 | global batch size: 512 | lm loss: 4.976362E+00 | loss scale: 8192.0 | grad norm: 0.366 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.673 | TFLOPs: 64.71 | +[default7]: iteration 715/ 3814 | consumed samples: 366080 | consumed tokens: 749731840 | elapsed time per iteration (s): 5.99 | learning rate: 5.064E-04 | global batch size: 512 | lm loss: 4.916146E+00 | loss scale: 8192.0 | grad norm: 0.293 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.490 | TFLOPs: 64.57 | +[default7]: iteration 716/ 3814 | consumed samples: 366592 | consumed tokens: 750780416 | elapsed time per iteration (s): 5.66 | learning rate: 5.063E-04 | global batch size: 512 | lm loss: 4.954202E+00 | loss scale: 8192.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.518 | TFLOPs: 68.37 | +[default7]: iteration 717/ 3814 | consumed samples: 367104 | consumed tokens: 751828992 | elapsed time per iteration (s): 5.96 | learning rate: 5.063E-04 | global batch size: 512 | lm loss: 4.918904E+00 | loss scale: 8192.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.869 | TFLOPs: 64.86 | +[default7]: iteration 718/ 3814 | consumed samples: 367616 | consumed tokens: 752877568 | elapsed time per iteration (s): 6.09 | learning rate: 5.062E-04 | global batch size: 512 | lm loss: 4.959902E+00 | loss scale: 8192.0 | grad norm: 0.274 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.037 | TFLOPs: 63.47 | +[default7]: iteration 719/ 3814 | consumed samples: 368128 | consumed tokens: 753926144 | elapsed time per iteration (s): 5.98 | learning rate: 5.061E-04 | global batch size: 512 | lm loss: 4.937943E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.647 | TFLOPs: 64.69 | +[default7]: iteration 720/ 3814 | consumed samples: 368640 | consumed tokens: 754974720 | elapsed time per iteration (s): 6.00 | learning rate: 5.060E-04 | global batch size: 512 | lm loss: 4.940960E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.288 | TFLOPs: 64.42 | +[default7]: iteration 721/ 3814 | consumed samples: 369152 | consumed tokens: 756023296 | elapsed time per iteration (s): 6.00 | learning rate: 5.060E-04 | global batch size: 512 | lm loss: 4.938623E+00 | loss scale: 8192.0 | grad norm: 0.256 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.312 | TFLOPs: 64.44 | +[default7]: iteration 722/ 3814 | consumed samples: 369664 | consumed tokens: 757071872 | elapsed time per iteration (s): 5.71 | learning rate: 5.059E-04 | global batch size: 512 | lm loss: 4.928513E+00 | loss scale: 8192.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.715 | TFLOPs: 67.76 | +[default7]: iteration 723/ 3814 | consumed samples: 370176 | consumed tokens: 758120448 | elapsed time per iteration (s): 5.94 | learning rate: 5.058E-04 | global batch size: 512 | lm loss: 4.934126E+00 | loss scale: 8192.0 | grad norm: 0.251 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.204 | TFLOPs: 65.11 | +[default7]: iteration 724/ 3814 | consumed samples: 370688 | consumed tokens: 759169024 | elapsed time per iteration (s): 5.95 | learning rate: 5.057E-04 | global batch size: 512 | lm loss: 4.895813E+00 | loss scale: 8192.0 | grad norm: 0.248 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.040 | TFLOPs: 64.99 | +[default7]: iteration 725/ 3814 | consumed samples: 371200 | consumed tokens: 760217600 | elapsed time per iteration (s): 5.97 | learning rate: 5.056E-04 | global batch size: 512 | lm loss: 4.918781E+00 | loss scale: 8192.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.801 | TFLOPs: 64.81 | +[default7]: iteration 726/ 3814 | consumed samples: 371712 | consumed tokens: 761266176 | elapsed time per iteration (s): 5.65 | learning rate: 5.056E-04 | global batch size: 512 | lm loss: 4.929324E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.632 | TFLOPs: 68.46 | +[default7]: iteration 727/ 3814 | consumed samples: 372224 | consumed tokens: 762314752 | elapsed time per iteration (s): 5.96 | learning rate: 5.055E-04 | global batch size: 512 | lm loss: 4.895501E+00 | loss scale: 8192.0 | grad norm: 0.224 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.932 | TFLOPs: 64.91 | +[default7]: iteration 728/ 3814 | consumed samples: 372736 | consumed tokens: 763363328 | elapsed time per iteration (s): 5.94 | learning rate: 5.054E-04 | global batch size: 512 | lm loss: 4.902266E+00 | loss scale: 8192.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.253 | TFLOPs: 65.15 | +[default7]: iteration 729/ 3814 | consumed samples: 373248 | consumed tokens: 764411904 | elapsed time per iteration (s): 5.97 | learning rate: 5.053E-04 | global batch size: 512 | lm loss: 4.888854E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.747 | TFLOPs: 64.77 | +[default7]: iteration 730/ 3814 | consumed samples: 373760 | consumed tokens: 765460480 | elapsed time per iteration (s): 5.95 | learning rate: 5.053E-04 | global batch size: 512 | lm loss: 4.890331E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.994 | TFLOPs: 64.95 | +[default7]: iteration 731/ 3814 | consumed samples: 374272 | consumed tokens: 766509056 | elapsed time per iteration (s): 5.93 | learning rate: 5.052E-04 | global batch size: 512 | lm loss: 4.875780E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.397 | TFLOPs: 65.26 | +[default7]: iteration 732/ 3814 | consumed samples: 374784 | consumed tokens: 767557632 | elapsed time per iteration (s): 5.94 | learning rate: 5.051E-04 | global batch size: 512 | lm loss: 4.895887E+00 | loss scale: 8192.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.137 | TFLOPs: 65.06 | +[default7]: iteration 733/ 3814 | consumed samples: 375296 | consumed tokens: 768606208 | elapsed time per iteration (s): 5.95 | learning rate: 5.050E-04 | global batch size: 512 | lm loss: 4.884105E+00 | loss scale: 8192.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.094 | TFLOPs: 65.03 | +[default7]: iteration 734/ 3814 | consumed samples: 375808 | consumed tokens: 769654784 | elapsed time per iteration (s): 6.00 | learning rate: 5.049E-04 | global batch size: 512 | lm loss: 4.873758E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.300 | TFLOPs: 64.43 | +[default7]: iteration 735/ 3814 | consumed samples: 376320 | consumed tokens: 770703360 | elapsed time per iteration (s): 5.95 | learning rate: 5.049E-04 | global batch size: 512 | lm loss: 4.855923E+00 | loss scale: 8192.0 | grad norm: 0.231 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.089 | TFLOPs: 65.02 | +[default7]: iteration 736/ 3814 | consumed samples: 376832 | consumed tokens: 771751936 | elapsed time per iteration (s): 6.02 | learning rate: 5.048E-04 | global batch size: 512 | lm loss: 4.879933E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.017 | TFLOPs: 64.21 | +[default7]: iteration 737/ 3814 | consumed samples: 377344 | consumed tokens: 772800512 | elapsed time per iteration (s): 5.98 | learning rate: 5.047E-04 | global batch size: 512 | lm loss: 4.855598E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.684 | TFLOPs: 64.72 | +[default7]: iteration 738/ 3814 | consumed samples: 377856 | consumed tokens: 773849088 | elapsed time per iteration (s): 5.98 | learning rate: 5.046E-04 | global batch size: 512 | lm loss: 4.876186E+00 | loss scale: 8192.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.636 | TFLOPs: 64.68 | +[default7]: iteration 739/ 3814 | consumed samples: 378368 | consumed tokens: 774897664 | elapsed time per iteration (s): 5.94 | learning rate: 5.045E-04 | global batch size: 512 | lm loss: 4.859134E+00 | loss scale: 8192.0 | grad norm: 0.298 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.151 | TFLOPs: 65.07 | +[default7]: iteration 740/ 3814 | consumed samples: 378880 | consumed tokens: 775946240 | elapsed time per iteration (s): 5.96 | learning rate: 5.045E-04 | global batch size: 512 | lm loss: 4.879177E+00 | loss scale: 8192.0 | grad norm: 0.294 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.943 | TFLOPs: 64.91 | +[default7]: iteration 741/ 3814 | consumed samples: 379392 | consumed tokens: 776994816 | elapsed time per iteration (s): 6.00 | learning rate: 5.044E-04 | global batch size: 512 | lm loss: 4.857681E+00 | loss scale: 8192.0 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.377 | TFLOPs: 64.49 | +[default7]: iteration 742/ 3814 | consumed samples: 379904 | consumed tokens: 778043392 | elapsed time per iteration (s): 5.96 | learning rate: 5.043E-04 | global batch size: 512 | lm loss: 4.855114E+00 | loss scale: 8192.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.925 | TFLOPs: 64.90 | +[default7]: iteration 743/ 3814 | consumed samples: 380416 | consumed tokens: 779091968 | elapsed time per iteration (s): 5.94 | learning rate: 5.042E-04 | global batch size: 512 | lm loss: 4.852895E+00 | loss scale: 8192.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.207 | TFLOPs: 65.11 | +[default7]: iteration 744/ 3814 | consumed samples: 380928 | consumed tokens: 780140544 | elapsed time per iteration (s): 6.01 | learning rate: 5.041E-04 | global batch size: 512 | lm loss: 4.841257E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.193 | TFLOPs: 64.35 | +[default7]: iteration 745/ 3814 | consumed samples: 381440 | consumed tokens: 781189120 | elapsed time per iteration (s): 5.97 | learning rate: 5.041E-04 | global batch size: 512 | lm loss: 4.834820E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.809 | TFLOPs: 64.81 | +[default7]: iteration 746/ 3814 | consumed samples: 381952 | consumed tokens: 782237696 | elapsed time per iteration (s): 5.92 | learning rate: 5.040E-04 | global batch size: 512 | lm loss: 4.841514E+00 | loss scale: 8192.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.538 | TFLOPs: 65.36 | +[default7]: iteration 747/ 3814 | consumed samples: 382464 | consumed tokens: 783286272 | elapsed time per iteration (s): 6.01 | learning rate: 5.039E-04 | global batch size: 512 | lm loss: 4.867319E+00 | loss scale: 8192.0 | grad norm: 0.277 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.173 | TFLOPs: 64.33 | +[default7]: iteration 748/ 3814 | consumed samples: 382976 | consumed tokens: 784334848 | elapsed time per iteration (s): 5.99 | learning rate: 5.038E-04 | global batch size: 512 | lm loss: 4.841736E+00 | loss scale: 8192.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.500 | TFLOPs: 64.58 | +[default7]: iteration 749/ 3814 | consumed samples: 383488 | consumed tokens: 785383424 | elapsed time per iteration (s): 5.99 | learning rate: 5.037E-04 | global batch size: 512 | lm loss: 4.840343E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.457 | TFLOPs: 64.55 | +[default7]: iteration 750/ 3814 | consumed samples: 384000 | consumed tokens: 786432000 | elapsed time per iteration (s): 5.99 | learning rate: 5.036E-04 | global batch size: 512 | lm loss: 4.832947E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.443 | TFLOPs: 64.54 | +[default1]:[2023-02-16 08:47:20,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 08:47:20,484] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step750 is begin to save! +[default0]:[2023-02-16 08:47:20,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:20,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:20,645] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:20,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:20,654] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:20,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:20,712] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:20,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:20,703] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:20,762] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:20,763] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:20,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:20,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:20,819] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:20,820] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:20,880] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:20,881] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:20,837] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:20,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:20,896] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:20,896] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:20,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:20,943] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:20,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:20,964] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,006] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,006] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,073] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:21,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,134] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,134] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,192] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_01-model_states.pt. +[default0]:[2023-02-16 08:47:21,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,158] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:21,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,219] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,193] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,284] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,312] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,369] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,343] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:21,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,492] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,468] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,469] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,553] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,528] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:21,586] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,586] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,613] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,676] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,652] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:21,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,712] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,736] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,771] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,771] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,795] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,853] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,833] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:21,891] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,892] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:21,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:21,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:21,973] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:21,953] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:21,953] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:22,011] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,012] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:22,035] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:22,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,073] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:22,096] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:22,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:22,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,134] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:22,191] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,192] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:22,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,211] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:22,277] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,277] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:22,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,251] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:22,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,319] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:22,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:22,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,393] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:22,381] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,381] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:22,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,449] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 08:47:22,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,440] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:22,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,500] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 08:47:22,506] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,507] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:22,566] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,566] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 08:47:22,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 08:47:22,568] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_01_model_states.pt +[default1]:[2023-02-16 08:47:22,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 08:47:22,571] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 08:47:22,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,559] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:22,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,614] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 08:47:22,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 08:47:22,616] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_00_model_states.pt +[default0]:[2023-02-16 08:47:22,616] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 08:47:22,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/mp_rank_00_model_states.pt. +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 08:47:22,658] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 08:47:23,156] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,156] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,156] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,212] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,196] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,182] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,182] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,182] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,201] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,201] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,201] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,238] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,238] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,165] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,165] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,165] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,218] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,218] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,251] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,251] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,198] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,198] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,215] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,215] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,215] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,207] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,208] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,217] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,217] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,223] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,223] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,223] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,265] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,300] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,300] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,231] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,231] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,231] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,313] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,281] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,321] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,309] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,310] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,310] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,287] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,319] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,287] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,291] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,291] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,341] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,326] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,327] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,338] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,322] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,340] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,320] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,333] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,334] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,334] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,365] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,365] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,392] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,323] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,323] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,352] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,318] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,389] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,338] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,338] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,336] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,386] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,386] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,320] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default2]:[2023-02-16 08:47:23,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 08:47:23,325] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 08:47:23,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,370] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,370] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default0]:[2023-02-16 08:47:23,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 08:47:23,363] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 08:47:23,363] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,394] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,394] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default3]:[2023-02-16 08:47:23,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,353] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,394] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,342] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,417] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,417] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,417] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,354] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,354] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default3]:[2023-02-16 08:47:23,343] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 08:47:23,343] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 08:47:23,344] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,369] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,369] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,369] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,392] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,392] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,392] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,400] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,400] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default1]:[2023-02-16 08:47:23,358] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,359] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,426] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,426] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default5]:[2023-02-16 08:47:23,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 08:47:23,426] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 08:47:23,426] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,411] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,411] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default4]:[2023-02-16 08:47:23,372] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 08:47:23,372] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 08:47:23,372] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default6]:[2023-02-16 08:47:23,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 08:47:23,453] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 08:47:23,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,437] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:time (ms) | save-checkpoint: 2988.50 +[default0]: successfully saved checkpoint at iteration 750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default1]:[2023-02-16 08:47:23,471] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 08:47:23,471] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 08:47:23,471] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]:[2023-02-16 08:47:23,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 08:47:23,456] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step750/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 08:47:23,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step750 is ready now! +[default7]: iteration 751/ 3814 | consumed samples: 384512 | consumed tokens: 787480576 | elapsed time per iteration (s): 8.95 | learning rate: 5.036E-04 | global batch size: 512 | lm loss: 4.827442E+00 | loss scale: 8192.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 57.194 | TFLOPs: 43.20 | +[default7]: iteration 752/ 3814 | consumed samples: 385024 | consumed tokens: 788529152 | elapsed time per iteration (s): 5.94 | learning rate: 5.035E-04 | global batch size: 512 | lm loss: 4.832355E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.142 | TFLOPs: 65.06 | +[default7]: iteration 753/ 3814 | consumed samples: 385536 | consumed tokens: 789577728 | elapsed time per iteration (s): 5.95 | learning rate: 5.034E-04 | global batch size: 512 | lm loss: 4.822669E+00 | loss scale: 8192.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.023 | TFLOPs: 64.97 | +[default7]: iteration 754/ 3814 | consumed samples: 386048 | consumed tokens: 790626304 | elapsed time per iteration (s): 5.97 | learning rate: 5.033E-04 | global batch size: 512 | lm loss: 4.827100E+00 | loss scale: 8192.0 | grad norm: 0.317 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.776 | TFLOPs: 64.79 | +[default7]: iteration 755/ 3814 | consumed samples: 386560 | consumed tokens: 791674880 | elapsed time per iteration (s): 5.94 | learning rate: 5.032E-04 | global batch size: 512 | lm loss: 4.825362E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.159 | TFLOPs: 65.08 | +[default7]: iteration 756/ 3814 | consumed samples: 387072 | consumed tokens: 792723456 | elapsed time per iteration (s): 6.00 | learning rate: 5.031E-04 | global batch size: 512 | lm loss: 4.840221E+00 | loss scale: 8192.0 | grad norm: 0.308 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.350 | TFLOPs: 64.47 | +[default7]: iteration 757/ 3814 | consumed samples: 387584 | consumed tokens: 793772032 | elapsed time per iteration (s): 6.03 | learning rate: 5.031E-04 | global batch size: 512 | lm loss: 4.844983E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.896 | TFLOPs: 64.12 | +[default7]: iteration 758/ 3814 | consumed samples: 388096 | consumed tokens: 794820608 | elapsed time per iteration (s): 5.99 | learning rate: 5.030E-04 | global batch size: 512 | lm loss: 4.815758E+00 | loss scale: 8192.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.439 | TFLOPs: 64.53 | +[default7]: iteration 759/ 3814 | consumed samples: 388608 | consumed tokens: 795869184 | elapsed time per iteration (s): 5.96 | learning rate: 5.029E-04 | global batch size: 512 | lm loss: 4.794550E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.899 | TFLOPs: 64.88 | +[default7]: iteration 760/ 3814 | consumed samples: 389120 | consumed tokens: 796917760 | elapsed time per iteration (s): 5.95 | learning rate: 5.028E-04 | global batch size: 512 | lm loss: 4.782942E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.029 | TFLOPs: 64.98 | +[default7]: iteration 761/ 3814 | consumed samples: 389632 | consumed tokens: 797966336 | elapsed time per iteration (s): 5.99 | learning rate: 5.027E-04 | global batch size: 512 | lm loss: 4.794396E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.487 | TFLOPs: 64.57 | +[default7]: iteration 762/ 3814 | consumed samples: 390144 | consumed tokens: 799014912 | elapsed time per iteration (s): 5.95 | learning rate: 5.026E-04 | global batch size: 512 | lm loss: 4.798491E+00 | loss scale: 8192.0 | grad norm: 0.266 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.109 | TFLOPs: 65.04 | +[default7]: iteration 763/ 3814 | consumed samples: 390656 | consumed tokens: 800063488 | elapsed time per iteration (s): 6.00 | learning rate: 5.026E-04 | global batch size: 512 | lm loss: 4.791668E+00 | loss scale: 8192.0 | grad norm: 0.265 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.309 | TFLOPs: 64.43 | +[default7]: iteration 764/ 3814 | consumed samples: 391168 | consumed tokens: 801112064 | elapsed time per iteration (s): 5.94 | learning rate: 5.025E-04 | global batch size: 512 | lm loss: 4.796085E+00 | loss scale: 8192.0 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.149 | TFLOPs: 65.07 | +[default7]: iteration 765/ 3814 | consumed samples: 391680 | consumed tokens: 802160640 | elapsed time per iteration (s): 5.95 | learning rate: 5.024E-04 | global batch size: 512 | lm loss: 4.810339E+00 | loss scale: 8192.0 | grad norm: 0.281 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.030 | TFLOPs: 64.98 | +[default7]: iteration 766/ 3814 | consumed samples: 392192 | consumed tokens: 803209216 | elapsed time per iteration (s): 6.00 | learning rate: 5.023E-04 | global batch size: 512 | lm loss: 4.774881E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.401 | TFLOPs: 64.50 | +[default7]: iteration 767/ 3814 | consumed samples: 392704 | consumed tokens: 804257792 | elapsed time per iteration (s): 5.97 | learning rate: 5.022E-04 | global batch size: 512 | lm loss: 4.794920E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.816 | TFLOPs: 64.82 | +[default7]: iteration 768/ 3814 | consumed samples: 393216 | consumed tokens: 805306368 | elapsed time per iteration (s): 5.90 | learning rate: 5.021E-04 | global batch size: 512 | lm loss: 4.776607E+00 | loss scale: 8192.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.708 | TFLOPs: 65.49 | +[default7]: iteration 769/ 3814 | consumed samples: 393728 | consumed tokens: 806354944 | elapsed time per iteration (s): 5.95 | learning rate: 5.020E-04 | global batch size: 512 | lm loss: 4.757502E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.067 | TFLOPs: 65.01 | +[default7]: iteration 770/ 3814 | consumed samples: 394240 | consumed tokens: 807403520 | elapsed time per iteration (s): 6.03 | learning rate: 5.020E-04 | global batch size: 512 | lm loss: 4.769960E+00 | loss scale: 8192.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.910 | TFLOPs: 64.13 | +[default7]: iteration 771/ 3814 | consumed samples: 394752 | consumed tokens: 808452096 | elapsed time per iteration (s): 6.06 | learning rate: 5.019E-04 | global batch size: 512 | lm loss: 4.746890E+00 | loss scale: 8192.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.488 | TFLOPs: 63.81 | +[default7]: iteration 772/ 3814 | consumed samples: 395264 | consumed tokens: 809500672 | elapsed time per iteration (s): 6.05 | learning rate: 5.018E-04 | global batch size: 512 | lm loss: 4.760268E+00 | loss scale: 8192.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.637 | TFLOPs: 63.93 | +[default7]: iteration 773/ 3814 | consumed samples: 395776 | consumed tokens: 810549248 | elapsed time per iteration (s): 6.08 | learning rate: 5.017E-04 | global batch size: 512 | lm loss: 4.744777E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.172 | TFLOPs: 63.58 | +[default7]: iteration 774/ 3814 | consumed samples: 396288 | consumed tokens: 811597824 | elapsed time per iteration (s): 5.95 | learning rate: 5.016E-04 | global batch size: 512 | lm loss: 4.752175E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.044 | TFLOPs: 64.99 | +[default7]: iteration 775/ 3814 | consumed samples: 396800 | consumed tokens: 812646400 | elapsed time per iteration (s): 6.07 | learning rate: 5.015E-04 | global batch size: 512 | lm loss: 4.776040E+00 | loss scale: 8192.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.339 | TFLOPs: 63.70 | +[default7]: iteration 776/ 3814 | consumed samples: 397312 | consumed tokens: 813694976 | elapsed time per iteration (s): 6.00 | learning rate: 5.014E-04 | global batch size: 512 | lm loss: 4.765540E+00 | loss scale: 8192.0 | grad norm: 0.310 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.337 | TFLOPs: 64.46 | +[default7]: iteration 777/ 3814 | consumed samples: 397824 | consumed tokens: 814743552 | elapsed time per iteration (s): 5.98 | learning rate: 5.013E-04 | global batch size: 512 | lm loss: 4.803652E+00 | loss scale: 8192.0 | grad norm: 0.407 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.563 | TFLOPs: 64.63 | +[default7]: iteration 778/ 3814 | consumed samples: 398336 | consumed tokens: 815792128 | elapsed time per iteration (s): 6.04 | learning rate: 5.013E-04 | global batch size: 512 | lm loss: 4.762078E+00 | loss scale: 8192.0 | grad norm: 0.369 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.780 | TFLOPs: 64.03 | +[default7]: iteration 779/ 3814 | consumed samples: 398848 | consumed tokens: 816840704 | elapsed time per iteration (s): 6.07 | learning rate: 5.012E-04 | global batch size: 512 | lm loss: 4.769497E+00 | loss scale: 8192.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.282 | TFLOPs: 63.66 | +[default7]: iteration 780/ 3814 | consumed samples: 399360 | consumed tokens: 817889280 | elapsed time per iteration (s): 6.06 | learning rate: 5.011E-04 | global batch size: 512 | lm loss: 4.764555E+00 | loss scale: 8192.0 | grad norm: 0.329 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.446 | TFLOPs: 63.78 | +[default7]: iteration 781/ 3814 | consumed samples: 399872 | consumed tokens: 818937856 | elapsed time per iteration (s): 5.98 | learning rate: 5.010E-04 | global batch size: 512 | lm loss: 4.784955E+00 | loss scale: 8192.0 | grad norm: 0.264 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.639 | TFLOPs: 64.68 | +[default7]: iteration 782/ 3814 | consumed samples: 400384 | consumed tokens: 819986432 | elapsed time per iteration (s): 6.04 | learning rate: 5.009E-04 | global batch size: 512 | lm loss: 4.737375E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.814 | TFLOPs: 64.06 | +[default7]: iteration 783/ 3814 | consumed samples: 400896 | consumed tokens: 821035008 | elapsed time per iteration (s): 5.95 | learning rate: 5.008E-04 | global batch size: 512 | lm loss: 4.732286E+00 | loss scale: 8192.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.062 | TFLOPs: 65.00 | +[default7]: iteration 784/ 3814 | consumed samples: 401408 | consumed tokens: 822083584 | elapsed time per iteration (s): 5.92 | learning rate: 5.007E-04 | global batch size: 512 | lm loss: 4.711157E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.467 | TFLOPs: 65.31 | +[default7]: iteration 785/ 3814 | consumed samples: 401920 | consumed tokens: 823132160 | elapsed time per iteration (s): 6.06 | learning rate: 5.006E-04 | global batch size: 512 | lm loss: 4.714983E+00 | loss scale: 8192.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.458 | TFLOPs: 63.79 | +[default7]: iteration 786/ 3814 | consumed samples: 402432 | consumed tokens: 824180736 | elapsed time per iteration (s): 6.13 | learning rate: 5.005E-04 | global batch size: 512 | lm loss: 4.736296E+00 | loss scale: 8192.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.464 | TFLOPs: 63.04 | +[default7]: iteration 787/ 3814 | consumed samples: 402944 | consumed tokens: 825229312 | elapsed time per iteration (s): 5.97 | learning rate: 5.005E-04 | global batch size: 512 | lm loss: 4.733380E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.706 | TFLOPs: 64.73 | +[default7]: iteration 788/ 3814 | consumed samples: 403456 | consumed tokens: 826277888 | elapsed time per iteration (s): 5.99 | learning rate: 5.004E-04 | global batch size: 512 | lm loss: 4.720528E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.502 | TFLOPs: 64.58 | +[default7]: iteration 789/ 3814 | consumed samples: 403968 | consumed tokens: 827326464 | elapsed time per iteration (s): 5.95 | learning rate: 5.003E-04 | global batch size: 512 | lm loss: 4.717013E+00 | loss scale: 8192.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.006 | TFLOPs: 64.96 | +[default7]: iteration 790/ 3814 | consumed samples: 404480 | consumed tokens: 828375040 | elapsed time per iteration (s): 6.01 | learning rate: 5.002E-04 | global batch size: 512 | lm loss: 4.698538E+00 | loss scale: 8192.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.190 | TFLOPs: 64.34 | +[default7]: iteration 791/ 3814 | consumed samples: 404992 | consumed tokens: 829423616 | elapsed time per iteration (s): 5.93 | learning rate: 5.001E-04 | global batch size: 512 | lm loss: 4.698759E+00 | loss scale: 8192.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.292 | TFLOPs: 65.18 | +[default7]: iteration 792/ 3814 | consumed samples: 405504 | consumed tokens: 830472192 | elapsed time per iteration (s): 6.04 | learning rate: 5.000E-04 | global batch size: 512 | lm loss: 4.736193E+00 | loss scale: 8192.0 | grad norm: 0.314 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.809 | TFLOPs: 64.06 | +[default7]: iteration 793/ 3814 | consumed samples: 406016 | consumed tokens: 831520768 | elapsed time per iteration (s): 6.03 | learning rate: 4.999E-04 | global batch size: 512 | lm loss: 4.717338E+00 | loss scale: 8192.0 | grad norm: 0.290 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.970 | TFLOPs: 64.18 | +[default7]: iteration 794/ 3814 | consumed samples: 406528 | consumed tokens: 832569344 | elapsed time per iteration (s): 5.99 | learning rate: 4.998E-04 | global batch size: 512 | lm loss: 4.707940E+00 | loss scale: 8192.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.489 | TFLOPs: 64.57 | +[default7]: iteration 795/ 3814 | consumed samples: 407040 | consumed tokens: 833617920 | elapsed time per iteration (s): 6.09 | learning rate: 4.997E-04 | global batch size: 512 | lm loss: 4.706094E+00 | loss scale: 8192.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.117 | TFLOPs: 63.53 | +[default7]: iteration 796/ 3814 | consumed samples: 407552 | consumed tokens: 834666496 | elapsed time per iteration (s): 6.04 | learning rate: 4.996E-04 | global batch size: 512 | lm loss: 4.699389E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.746 | TFLOPs: 64.01 | +[default7]: iteration 797/ 3814 | consumed samples: 408064 | consumed tokens: 835715072 | elapsed time per iteration (s): 6.03 | learning rate: 4.995E-04 | global batch size: 512 | lm loss: 4.699966E+00 | loss scale: 8192.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.966 | TFLOPs: 64.18 | +[default7]: iteration 798/ 3814 | consumed samples: 408576 | consumed tokens: 836763648 | elapsed time per iteration (s): 6.11 | learning rate: 4.995E-04 | global batch size: 512 | lm loss: 4.668324E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.840 | TFLOPs: 63.32 | +[default7]: iteration 799/ 3814 | consumed samples: 409088 | consumed tokens: 837812224 | elapsed time per iteration (s): 6.05 | learning rate: 4.994E-04 | global batch size: 512 | lm loss: 4.697263E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.616 | TFLOPs: 63.91 | +[default7]: iteration 800/ 3814 | consumed samples: 409600 | consumed tokens: 838860800 | elapsed time per iteration (s): 5.96 | learning rate: 4.993E-04 | global batch size: 512 | lm loss: 4.689942E+00 | loss scale: 8192.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.869 | TFLOPs: 64.86 | +[default7]: iteration 801/ 3814 | consumed samples: 410112 | consumed tokens: 839909376 | elapsed time per iteration (s): 5.99 | learning rate: 4.992E-04 | global batch size: 512 | lm loss: 4.702653E+00 | loss scale: 8192.0 | grad norm: 0.361 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.522 | TFLOPs: 64.60 | +[default7]: iteration 802/ 3814 | consumed samples: 410624 | consumed tokens: 840957952 | elapsed time per iteration (s): 5.95 | learning rate: 4.991E-04 | global batch size: 512 | lm loss: 4.682058E+00 | loss scale: 8192.0 | grad norm: 0.321 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.028 | TFLOPs: 64.98 | +[default7]: iteration 803/ 3814 | consumed samples: 411136 | consumed tokens: 842006528 | elapsed time per iteration (s): 6.06 | learning rate: 4.990E-04 | global batch size: 512 | lm loss: 4.721493E+00 | loss scale: 8192.0 | grad norm: 0.272 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.474 | TFLOPs: 63.80 | +[default7]: iteration 804/ 3814 | consumed samples: 411648 | consumed tokens: 843055104 | elapsed time per iteration (s): 5.98 | learning rate: 4.989E-04 | global batch size: 512 | lm loss: 4.709596E+00 | loss scale: 8192.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.619 | TFLOPs: 64.67 | +[default7]: iteration 805/ 3814 | consumed samples: 412160 | consumed tokens: 844103680 | elapsed time per iteration (s): 5.98 | learning rate: 4.988E-04 | global batch size: 512 | lm loss: 4.689207E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.589 | TFLOPs: 64.65 | +[default7]: iteration 806/ 3814 | consumed samples: 412672 | consumed tokens: 845152256 | elapsed time per iteration (s): 6.07 | learning rate: 4.987E-04 | global batch size: 512 | lm loss: 4.698794E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.375 | TFLOPs: 63.73 | +[default7]: iteration 807/ 3814 | consumed samples: 413184 | consumed tokens: 846200832 | elapsed time per iteration (s): 5.96 | learning rate: 4.986E-04 | global batch size: 512 | lm loss: 4.692599E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.946 | TFLOPs: 64.92 | +[default7]: iteration 808/ 3814 | consumed samples: 413696 | consumed tokens: 847249408 | elapsed time per iteration (s): 5.86 | learning rate: 4.985E-04 | global batch size: 512 | lm loss: 4.657340E+00 | loss scale: 8192.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.322 | TFLOPs: 65.96 | +[default7]: iteration 809/ 3814 | consumed samples: 414208 | consumed tokens: 848297984 | elapsed time per iteration (s): 6.09 | learning rate: 4.984E-04 | global batch size: 512 | lm loss: 4.667279E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.039 | TFLOPs: 63.48 | +[default7]: iteration 810/ 3814 | consumed samples: 414720 | consumed tokens: 849346560 | elapsed time per iteration (s): 5.80 | learning rate: 4.983E-04 | global batch size: 512 | lm loss: 4.651710E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.338 | TFLOPs: 66.72 | +[default7]: iteration 811/ 3814 | consumed samples: 415232 | consumed tokens: 850395136 | elapsed time per iteration (s): 5.98 | learning rate: 4.982E-04 | global batch size: 512 | lm loss: 4.633029E+00 | loss scale: 8192.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.651 | TFLOPs: 64.69 | +[default7]: iteration 812/ 3814 | consumed samples: 415744 | consumed tokens: 851443712 | elapsed time per iteration (s): 5.66 | learning rate: 4.981E-04 | global batch size: 512 | lm loss: 4.647582E+00 | loss scale: 8192.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.400 | TFLOPs: 68.28 | +[default7]: iteration 813/ 3814 | consumed samples: 416256 | consumed tokens: 852492288 | elapsed time per iteration (s): 5.98 | learning rate: 4.981E-04 | global batch size: 512 | lm loss: 4.624917E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.686 | TFLOPs: 64.72 | +[default7]: iteration 814/ 3814 | consumed samples: 416768 | consumed tokens: 853540864 | elapsed time per iteration (s): 6.09 | learning rate: 4.980E-04 | global batch size: 512 | lm loss: 4.657001E+00 | loss scale: 8192.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.006 | TFLOPs: 63.45 | +[default7]: iteration 815/ 3814 | consumed samples: 417280 | consumed tokens: 854589440 | elapsed time per iteration (s): 6.05 | learning rate: 4.979E-04 | global batch size: 512 | lm loss: 4.669936E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.598 | TFLOPs: 63.90 | +[default7]: iteration 816/ 3814 | consumed samples: 417792 | consumed tokens: 855638016 | elapsed time per iteration (s): 6.02 | learning rate: 4.978E-04 | global batch size: 512 | lm loss: 4.675426E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.044 | TFLOPs: 64.23 | +[default7]: iteration 817/ 3814 | consumed samples: 418304 | consumed tokens: 856686592 | elapsed time per iteration (s): 5.96 | learning rate: 4.977E-04 | global batch size: 512 | lm loss: 4.666538E+00 | loss scale: 8192.0 | grad norm: 0.292 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.932 | TFLOPs: 64.91 | +[default7]: iteration 818/ 3814 | consumed samples: 418816 | consumed tokens: 857735168 | elapsed time per iteration (s): 5.85 | learning rate: 4.976E-04 | global batch size: 512 | lm loss: 4.690305E+00 | loss scale: 8192.0 | grad norm: 0.318 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.489 | TFLOPs: 66.08 | +[default7]: iteration 819/ 3814 | consumed samples: 419328 | consumed tokens: 858783744 | elapsed time per iteration (s): 5.95 | learning rate: 4.975E-04 | global batch size: 512 | lm loss: 4.663669E+00 | loss scale: 8192.0 | grad norm: 0.315 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.024 | TFLOPs: 64.97 | +[default7]: iteration 820/ 3814 | consumed samples: 419840 | consumed tokens: 859832320 | elapsed time per iteration (s): 5.96 | learning rate: 4.974E-04 | global batch size: 512 | lm loss: 4.644549E+00 | loss scale: 8192.0 | grad norm: 0.261 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.882 | TFLOPs: 64.87 | +[default7]: iteration 821/ 3814 | consumed samples: 420352 | consumed tokens: 860880896 | elapsed time per iteration (s): 6.02 | learning rate: 4.973E-04 | global batch size: 512 | lm loss: 4.663504E+00 | loss scale: 8192.0 | grad norm: 0.307 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.002 | TFLOPs: 64.20 | +[default7]: iteration 822/ 3814 | consumed samples: 420864 | consumed tokens: 861929472 | elapsed time per iteration (s): 5.98 | learning rate: 4.972E-04 | global batch size: 512 | lm loss: 4.682642E+00 | loss scale: 8192.0 | grad norm: 0.357 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.588 | TFLOPs: 64.65 | +[default7]: iteration 823/ 3814 | consumed samples: 421376 | consumed tokens: 862978048 | elapsed time per iteration (s): 5.92 | learning rate: 4.971E-04 | global batch size: 512 | lm loss: 4.652049E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.463 | TFLOPs: 65.31 | +[default7]: iteration 824/ 3814 | consumed samples: 421888 | consumed tokens: 864026624 | elapsed time per iteration (s): 6.08 | learning rate: 4.970E-04 | global batch size: 512 | lm loss: 4.645546E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.172 | TFLOPs: 63.58 | +[default7]: iteration 825/ 3814 | consumed samples: 422400 | consumed tokens: 865075200 | elapsed time per iteration (s): 5.88 | learning rate: 4.969E-04 | global batch size: 512 | lm loss: 4.657433E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.008 | TFLOPs: 65.72 | +[default7]: iteration 826/ 3814 | consumed samples: 422912 | consumed tokens: 866123776 | elapsed time per iteration (s): 5.95 | learning rate: 4.968E-04 | global batch size: 512 | lm loss: 4.640855E+00 | loss scale: 8192.0 | grad norm: 0.262 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.021 | TFLOPs: 64.97 | +[default7]: iteration 827/ 3814 | consumed samples: 423424 | consumed tokens: 867172352 | elapsed time per iteration (s): 6.04 | learning rate: 4.967E-04 | global batch size: 512 | lm loss: 4.652851E+00 | loss scale: 8192.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.823 | TFLOPs: 64.07 | +[default7]: iteration 828/ 3814 | consumed samples: 423936 | consumed tokens: 868220928 | elapsed time per iteration (s): 6.02 | learning rate: 4.966E-04 | global batch size: 512 | lm loss: 4.646973E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.084 | TFLOPs: 64.26 | +[default7]: iteration 829/ 3814 | consumed samples: 424448 | consumed tokens: 869269504 | elapsed time per iteration (s): 5.93 | learning rate: 4.965E-04 | global batch size: 512 | lm loss: 4.622712E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.385 | TFLOPs: 65.25 | +[default7]: iteration 830/ 3814 | consumed samples: 424960 | consumed tokens: 870318080 | elapsed time per iteration (s): 5.99 | learning rate: 4.964E-04 | global batch size: 512 | lm loss: 4.629492E+00 | loss scale: 8192.0 | grad norm: 0.252 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.407 | TFLOPs: 64.51 | +[default7]: iteration 831/ 3814 | consumed samples: 425472 | consumed tokens: 871366656 | elapsed time per iteration (s): 5.93 | learning rate: 4.963E-04 | global batch size: 512 | lm loss: 4.587540E+00 | loss scale: 8192.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.310 | TFLOPs: 65.19 | +[default7]: iteration 832/ 3814 | consumed samples: 425984 | consumed tokens: 872415232 | elapsed time per iteration (s): 5.99 | learning rate: 4.962E-04 | global batch size: 512 | lm loss: 4.617246E+00 | loss scale: 8192.0 | grad norm: 0.229 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.424 | TFLOPs: 64.52 | +[default7]: iteration 833/ 3814 | consumed samples: 426496 | consumed tokens: 873463808 | elapsed time per iteration (s): 5.92 | learning rate: 4.961E-04 | global batch size: 512 | lm loss: 4.620022E+00 | loss scale: 8192.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.432 | TFLOPs: 65.28 | +[default7]: iteration 834/ 3814 | consumed samples: 427008 | consumed tokens: 874512384 | elapsed time per iteration (s): 5.94 | learning rate: 4.960E-04 | global batch size: 512 | lm loss: 4.620600E+00 | loss scale: 8192.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.220 | TFLOPs: 65.12 | +[default7]: iteration 835/ 3814 | consumed samples: 427520 | consumed tokens: 875560960 | elapsed time per iteration (s): 5.98 | learning rate: 4.959E-04 | global batch size: 512 | lm loss: 4.561524E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.659 | TFLOPs: 64.70 | +[default7]: iteration 836/ 3814 | consumed samples: 428032 | consumed tokens: 876609536 | elapsed time per iteration (s): 5.98 | learning rate: 4.958E-04 | global batch size: 512 | lm loss: 4.598289E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.600 | TFLOPs: 64.65 | +[default7]: iteration 837/ 3814 | consumed samples: 428544 | consumed tokens: 877658112 | elapsed time per iteration (s): 5.97 | learning rate: 4.957E-04 | global batch size: 512 | lm loss: 4.595585E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.817 | TFLOPs: 64.82 | +[default7]: iteration 838/ 3814 | consumed samples: 429056 | consumed tokens: 878706688 | elapsed time per iteration (s): 5.92 | learning rate: 4.956E-04 | global batch size: 512 | lm loss: 4.592754E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.510 | TFLOPs: 65.34 | +[default7]: iteration 839/ 3814 | consumed samples: 429568 | consumed tokens: 879755264 | elapsed time per iteration (s): 5.95 | learning rate: 4.955E-04 | global batch size: 512 | lm loss: 4.595773E+00 | loss scale: 8192.0 | grad norm: 0.254 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.031 | TFLOPs: 64.98 | +[default7]: iteration 840/ 3814 | consumed samples: 430080 | consumed tokens: 880803840 | elapsed time per iteration (s): 5.70 | learning rate: 4.954E-04 | global batch size: 512 | lm loss: 4.599052E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.768 | TFLOPs: 67.80 | +[default7]: iteration 841/ 3814 | consumed samples: 430592 | consumed tokens: 881852416 | elapsed time per iteration (s): 5.97 | learning rate: 4.953E-04 | global batch size: 512 | lm loss: 4.602687E+00 | loss scale: 8192.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.798 | TFLOPs: 64.80 | +[default7]: iteration 842/ 3814 | consumed samples: 431104 | consumed tokens: 882900992 | elapsed time per iteration (s): 6.00 | learning rate: 4.952E-04 | global batch size: 512 | lm loss: 4.628788E+00 | loss scale: 8192.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.382 | TFLOPs: 64.49 | +[default7]: iteration 843/ 3814 | consumed samples: 431616 | consumed tokens: 883949568 | elapsed time per iteration (s): 6.01 | learning rate: 4.951E-04 | global batch size: 512 | lm loss: 4.596134E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.247 | TFLOPs: 64.39 | +[default7]: iteration 844/ 3814 | consumed samples: 432128 | consumed tokens: 884998144 | elapsed time per iteration (s): 5.94 | learning rate: 4.950E-04 | global batch size: 512 | lm loss: 4.592647E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.200 | TFLOPs: 65.11 | +[default7]: iteration 845/ 3814 | consumed samples: 432640 | consumed tokens: 886046720 | elapsed time per iteration (s): 5.93 | learning rate: 4.949E-04 | global batch size: 512 | lm loss: 4.620600E+00 | loss scale: 8192.0 | grad norm: 0.260 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.367 | TFLOPs: 65.23 | +[default7]: iteration 846/ 3814 | consumed samples: 433152 | consumed tokens: 887095296 | elapsed time per iteration (s): 5.98 | learning rate: 4.948E-04 | global batch size: 512 | lm loss: 4.608099E+00 | loss scale: 8192.0 | grad norm: 0.245 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.635 | TFLOPs: 64.68 | +[default7]: iteration 847/ 3814 | consumed samples: 433664 | consumed tokens: 888143872 | elapsed time per iteration (s): 5.97 | learning rate: 4.947E-04 | global batch size: 512 | lm loss: 4.573436E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.747 | TFLOPs: 64.77 | +[default7]: iteration 848/ 3814 | consumed samples: 434176 | consumed tokens: 889192448 | elapsed time per iteration (s): 5.97 | learning rate: 4.946E-04 | global batch size: 512 | lm loss: 4.582870E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.798 | TFLOPs: 64.80 | +[default7]: iteration 849/ 3814 | consumed samples: 434688 | consumed tokens: 890241024 | elapsed time per iteration (s): 5.94 | learning rate: 4.945E-04 | global batch size: 512 | lm loss: 4.567896E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.155 | TFLOPs: 65.07 | +[default7]: iteration 850/ 3814 | consumed samples: 435200 | consumed tokens: 891289600 | elapsed time per iteration (s): 5.96 | learning rate: 4.944E-04 | global batch size: 512 | lm loss: 4.572854E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.890 | TFLOPs: 64.87 | +[default7]: iteration 851/ 3814 | consumed samples: 435712 | consumed tokens: 892338176 | elapsed time per iteration (s): 5.91 | learning rate: 4.943E-04 | global batch size: 512 | lm loss: 4.596509E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.640 | TFLOPs: 65.44 | +[default7]: iteration 852/ 3814 | consumed samples: 436224 | consumed tokens: 893386752 | elapsed time per iteration (s): 5.92 | learning rate: 4.942E-04 | global batch size: 512 | lm loss: 4.570214E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.542 | TFLOPs: 65.37 | +[default7]: iteration 853/ 3814 | consumed samples: 436736 | consumed tokens: 894435328 | elapsed time per iteration (s): 5.97 | learning rate: 4.941E-04 | global batch size: 512 | lm loss: 4.557622E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.799 | TFLOPs: 64.80 | +[default7]: iteration 854/ 3814 | consumed samples: 437248 | consumed tokens: 895483904 | elapsed time per iteration (s): 5.95 | learning rate: 4.940E-04 | global batch size: 512 | lm loss: 4.535846E+00 | loss scale: 8192.0 | grad norm: 0.240 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.038 | TFLOPs: 64.99 | +[default7]: iteration 855/ 3814 | consumed samples: 437760 | consumed tokens: 896532480 | elapsed time per iteration (s): 6.00 | learning rate: 4.939E-04 | global batch size: 512 | lm loss: 4.560446E+00 | loss scale: 8192.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.310 | TFLOPs: 64.44 | +[default7]: iteration 856/ 3814 | consumed samples: 438272 | consumed tokens: 897581056 | elapsed time per iteration (s): 5.99 | learning rate: 4.938E-04 | global batch size: 512 | lm loss: 4.581931E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.527 | TFLOPs: 64.60 | +[default7]: iteration 857/ 3814 | consumed samples: 438784 | consumed tokens: 898629632 | elapsed time per iteration (s): 6.01 | learning rate: 4.937E-04 | global batch size: 512 | lm loss: 4.534554E+00 | loss scale: 8192.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.223 | TFLOPs: 64.37 | +[default7]: iteration 858/ 3814 | consumed samples: 439296 | consumed tokens: 899678208 | elapsed time per iteration (s): 6.02 | learning rate: 4.936E-04 | global batch size: 512 | lm loss: 4.555015E+00 | loss scale: 8192.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.069 | TFLOPs: 64.25 | +[default7]: iteration 859/ 3814 | consumed samples: 439808 | consumed tokens: 900726784 | elapsed time per iteration (s): 5.96 | learning rate: 4.935E-04 | global batch size: 512 | lm loss: 4.567818E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.866 | TFLOPs: 64.86 | +[default7]: iteration 860/ 3814 | consumed samples: 440320 | consumed tokens: 901775360 | elapsed time per iteration (s): 5.98 | learning rate: 4.934E-04 | global batch size: 512 | lm loss: 4.566259E+00 | loss scale: 8192.0 | grad norm: 0.239 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.622 | TFLOPs: 64.67 | +[default7]: iteration 861/ 3814 | consumed samples: 440832 | consumed tokens: 902823936 | elapsed time per iteration (s): 5.97 | learning rate: 4.933E-04 | global batch size: 512 | lm loss: 4.565556E+00 | loss scale: 8192.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.714 | TFLOPs: 64.74 | +[default7]: iteration 862/ 3814 | consumed samples: 441344 | consumed tokens: 903872512 | elapsed time per iteration (s): 5.96 | learning rate: 4.932E-04 | global batch size: 512 | lm loss: 4.540599E+00 | loss scale: 8192.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.863 | TFLOPs: 64.85 | +[default7]: iteration 863/ 3814 | consumed samples: 441856 | consumed tokens: 904921088 | elapsed time per iteration (s): 5.97 | learning rate: 4.931E-04 | global batch size: 512 | lm loss: 4.514649E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.812 | TFLOPs: 64.81 | +[default7]: iteration 864/ 3814 | consumed samples: 442368 | consumed tokens: 905969664 | elapsed time per iteration (s): 5.90 | learning rate: 4.930E-04 | global batch size: 512 | lm loss: 4.560269E+00 | loss scale: 8192.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.834 | TFLOPs: 65.59 | +[default7]: iteration 865/ 3814 | consumed samples: 442880 | consumed tokens: 907018240 | elapsed time per iteration (s): 5.98 | learning rate: 4.928E-04 | global batch size: 512 | lm loss: 4.519538E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.653 | TFLOPs: 64.69 | +[default7]: iteration 866/ 3814 | consumed samples: 443392 | consumed tokens: 908066816 | elapsed time per iteration (s): 6.00 | learning rate: 4.927E-04 | global batch size: 512 | lm loss: 4.520114E+00 | loss scale: 8192.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.297 | TFLOPs: 64.43 | +[default7]: iteration 867/ 3814 | consumed samples: 443904 | consumed tokens: 909115392 | elapsed time per iteration (s): 5.97 | learning rate: 4.926E-04 | global batch size: 512 | lm loss: 4.512193E+00 | loss scale: 8192.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.795 | TFLOPs: 64.80 | +[default7]: iteration 868/ 3814 | consumed samples: 444416 | consumed tokens: 910163968 | elapsed time per iteration (s): 5.94 | learning rate: 4.925E-04 | global batch size: 512 | lm loss: 4.496635E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.215 | TFLOPs: 65.12 | +[default7]: iteration 869/ 3814 | consumed samples: 444928 | consumed tokens: 911212544 | elapsed time per iteration (s): 5.99 | learning rate: 4.924E-04 | global batch size: 512 | lm loss: 4.524092E+00 | loss scale: 8192.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.517 | TFLOPs: 64.59 | +[default7]: iteration 870/ 3814 | consumed samples: 445440 | consumed tokens: 912261120 | elapsed time per iteration (s): 5.95 | learning rate: 4.923E-04 | global batch size: 512 | lm loss: 4.545441E+00 | loss scale: 8192.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.094 | TFLOPs: 65.03 | +[default7]: iteration 871/ 3814 | consumed samples: 445952 | consumed tokens: 913309696 | elapsed time per iteration (s): 5.94 | learning rate: 4.922E-04 | global batch size: 512 | lm loss: 4.528924E+00 | loss scale: 8192.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.136 | TFLOPs: 65.06 | +[default7]: iteration 872/ 3814 | consumed samples: 446464 | consumed tokens: 914358272 | elapsed time per iteration (s): 6.00 | learning rate: 4.921E-04 | global batch size: 512 | lm loss: 4.540662E+00 | loss scale: 8192.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.357 | TFLOPs: 64.47 | +[default7]: iteration 873/ 3814 | consumed samples: 446976 | consumed tokens: 915406848 | elapsed time per iteration (s): 5.98 | learning rate: 4.920E-04 | global batch size: 512 | lm loss: 4.543183E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.641 | TFLOPs: 64.69 | +[default7]: iteration 874/ 3814 | consumed samples: 447488 | consumed tokens: 916455424 | elapsed time per iteration (s): 5.96 | learning rate: 4.919E-04 | global batch size: 512 | lm loss: 4.515805E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.885 | TFLOPs: 64.87 | +[default7]: iteration 875/ 3814 | consumed samples: 448000 | consumed tokens: 917504000 | elapsed time per iteration (s): 5.96 | learning rate: 4.918E-04 | global batch size: 512 | lm loss: 4.495407E+00 | loss scale: 8192.0 | grad norm: 0.267 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.948 | TFLOPs: 64.92 | +[default7]: iteration 876/ 3814 | consumed samples: 448512 | consumed tokens: 918552576 | elapsed time per iteration (s): 5.97 | learning rate: 4.917E-04 | global batch size: 512 | lm loss: 4.516092E+00 | loss scale: 8192.0 | grad norm: 0.276 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.693 | TFLOPs: 64.72 | +[default7]: iteration 877/ 3814 | consumed samples: 449024 | consumed tokens: 919601152 | elapsed time per iteration (s): 5.95 | learning rate: 4.916E-04 | global batch size: 512 | lm loss: 4.529700E+00 | loss scale: 8192.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.104 | TFLOPs: 65.04 | +[default7]: iteration 878/ 3814 | consumed samples: 449536 | consumed tokens: 920649728 | elapsed time per iteration (s): 5.96 | learning rate: 4.915E-04 | global batch size: 512 | lm loss: 4.537807E+00 | loss scale: 8192.0 | grad norm: 0.286 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.927 | TFLOPs: 64.90 | +[default7]: iteration 879/ 3814 | consumed samples: 450048 | consumed tokens: 921698304 | elapsed time per iteration (s): 5.95 | learning rate: 4.914E-04 | global batch size: 512 | lm loss: 4.510390E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.037 | TFLOPs: 64.98 | +[default7]: iteration 880/ 3814 | consumed samples: 450560 | consumed tokens: 922746880 | elapsed time per iteration (s): 5.99 | learning rate: 4.913E-04 | global batch size: 512 | lm loss: 4.485783E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.484 | TFLOPs: 64.57 | +[default7]: iteration 881/ 3814 | consumed samples: 451072 | consumed tokens: 923795456 | elapsed time per iteration (s): 5.96 | learning rate: 4.911E-04 | global batch size: 512 | lm loss: 4.498448E+00 | loss scale: 8192.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.868 | TFLOPs: 64.86 | +[default7]: iteration 882/ 3814 | consumed samples: 451584 | consumed tokens: 924844032 | elapsed time per iteration (s): 5.96 | learning rate: 4.910E-04 | global batch size: 512 | lm loss: 4.503768E+00 | loss scale: 8192.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.924 | TFLOPs: 64.90 | +[default7]: iteration 883/ 3814 | consumed samples: 452096 | consumed tokens: 925892608 | elapsed time per iteration (s): 5.96 | learning rate: 4.909E-04 | global batch size: 512 | lm loss: 4.466969E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.845 | TFLOPs: 64.84 | +[default7]: iteration 884/ 3814 | consumed samples: 452608 | consumed tokens: 926941184 | elapsed time per iteration (s): 5.94 | learning rate: 4.908E-04 | global batch size: 512 | lm loss: 4.492115E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.123 | TFLOPs: 65.05 | +[default7]: iteration 885/ 3814 | consumed samples: 453120 | consumed tokens: 927989760 | elapsed time per iteration (s): 6.01 | learning rate: 4.907E-04 | global batch size: 512 | lm loss: 4.509772E+00 | loss scale: 8192.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.154 | TFLOPs: 64.32 | +[default7]: iteration 886/ 3814 | consumed samples: 453632 | consumed tokens: 929038336 | elapsed time per iteration (s): 5.96 | learning rate: 4.906E-04 | global batch size: 512 | lm loss: 4.496783E+00 | loss scale: 8192.0 | grad norm: 0.302 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.955 | TFLOPs: 64.92 | +[default7]: iteration 887/ 3814 | consumed samples: 454144 | consumed tokens: 930086912 | elapsed time per iteration (s): 5.99 | learning rate: 4.905E-04 | global batch size: 512 | lm loss: 4.456879E+00 | loss scale: 8192.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.416 | TFLOPs: 64.52 | +[default7]: iteration 888/ 3814 | consumed samples: 454656 | consumed tokens: 931135488 | elapsed time per iteration (s): 5.97 | learning rate: 4.904E-04 | global batch size: 512 | lm loss: 4.488525E+00 | loss scale: 8192.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.708 | TFLOPs: 64.74 | +[default7]: iteration 889/ 3814 | consumed samples: 455168 | consumed tokens: 932184064 | elapsed time per iteration (s): 5.95 | learning rate: 4.903E-04 | global batch size: 512 | lm loss: 4.487351E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.087 | TFLOPs: 65.02 | +[default7]: iteration 890/ 3814 | consumed samples: 455680 | consumed tokens: 933232640 | elapsed time per iteration (s): 6.00 | learning rate: 4.902E-04 | global batch size: 512 | lm loss: 4.488390E+00 | loss scale: 8192.0 | grad norm: 0.199 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.286 | TFLOPs: 64.42 | +[default7]: iteration 891/ 3814 | consumed samples: 456192 | consumed tokens: 934281216 | elapsed time per iteration (s): 5.95 | learning rate: 4.901E-04 | global batch size: 512 | lm loss: 4.484529E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.061 | TFLOPs: 65.00 | +[default7]: iteration 892/ 3814 | consumed samples: 456704 | consumed tokens: 935329792 | elapsed time per iteration (s): 5.65 | learning rate: 4.899E-04 | global batch size: 512 | lm loss: 4.473131E+00 | loss scale: 8192.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.567 | TFLOPs: 68.41 | +[default7]: iteration 893/ 3814 | consumed samples: 457216 | consumed tokens: 936378368 | elapsed time per iteration (s): 5.93 | learning rate: 4.898E-04 | global batch size: 512 | lm loss: 4.455779E+00 | loss scale: 8192.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.270 | TFLOPs: 65.16 | +[default7]: iteration 894/ 3814 | consumed samples: 457728 | consumed tokens: 937426944 | elapsed time per iteration (s): 5.99 | learning rate: 4.897E-04 | global batch size: 512 | lm loss: 4.478796E+00 | loss scale: 8192.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.541 | TFLOPs: 64.61 | +[default7]: iteration 895/ 3814 | consumed samples: 458240 | consumed tokens: 938475520 | elapsed time per iteration (s): 5.99 | learning rate: 4.896E-04 | global batch size: 512 | lm loss: 4.478446E+00 | loss scale: 8192.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.465 | TFLOPs: 64.55 | +[default7]: iteration 896/ 3814 | consumed samples: 458752 | consumed tokens: 939524096 | elapsed time per iteration (s): 5.96 | learning rate: 4.895E-04 | global batch size: 512 | lm loss: 4.469142E+00 | loss scale: 8192.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.853 | TFLOPs: 64.85 | +[default7]: iteration 897/ 3814 | consumed samples: 459264 | consumed tokens: 940572672 | elapsed time per iteration (s): 6.00 | learning rate: 4.894E-04 | global batch size: 512 | lm loss: 4.454826E+00 | loss scale: 8192.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.345 | TFLOPs: 64.46 | +[default7]: iteration 898/ 3814 | consumed samples: 459776 | consumed tokens: 941621248 | elapsed time per iteration (s): 5.71 | learning rate: 4.893E-04 | global batch size: 512 | lm loss: 4.423679E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.680 | TFLOPs: 67.74 | +[default7]: iteration 899/ 3814 | consumed samples: 460288 | consumed tokens: 942669824 | elapsed time per iteration (s): 6.01 | learning rate: 4.892E-04 | global batch size: 512 | lm loss: 4.463740E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.180 | TFLOPs: 64.34 | +[default7]: iteration 900/ 3814 | consumed samples: 460800 | consumed tokens: 943718400 | elapsed time per iteration (s): 6.04 | learning rate: 4.891E-04 | global batch size: 512 | lm loss: 4.455691E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.770 | TFLOPs: 64.03 | +[default7]: iteration 901/ 3814 | consumed samples: 461312 | consumed tokens: 944766976 | elapsed time per iteration (s): 5.98 | learning rate: 4.889E-04 | global batch size: 512 | lm loss: 4.461817E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.639 | TFLOPs: 64.68 | +[default7]: iteration 902/ 3814 | consumed samples: 461824 | consumed tokens: 945815552 | elapsed time per iteration (s): 5.96 | learning rate: 4.888E-04 | global batch size: 512 | lm loss: 4.439479E+00 | loss scale: 8192.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.882 | TFLOPs: 64.87 | +[default7]: iteration 903/ 3814 | consumed samples: 462336 | consumed tokens: 946864128 | elapsed time per iteration (s): 6.00 | learning rate: 4.887E-04 | global batch size: 512 | lm loss: 4.457850E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.380 | TFLOPs: 64.49 | +[default7]: iteration 904/ 3814 | consumed samples: 462848 | consumed tokens: 947912704 | elapsed time per iteration (s): 5.99 | learning rate: 4.886E-04 | global batch size: 512 | lm loss: 4.451580E+00 | loss scale: 8192.0 | grad norm: 0.331 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.442 | TFLOPs: 64.54 | +[default7]: iteration 905/ 3814 | consumed samples: 463360 | consumed tokens: 948961280 | elapsed time per iteration (s): 5.90 | learning rate: 4.885E-04 | global batch size: 512 | lm loss: 4.497948E+00 | loss scale: 8192.0 | grad norm: 0.345 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.785 | TFLOPs: 65.55 | +[default7]: iteration 906/ 3814 | consumed samples: 463872 | consumed tokens: 950009856 | elapsed time per iteration (s): 6.00 | learning rate: 4.884E-04 | global batch size: 512 | lm loss: 4.472414E+00 | loss scale: 8192.0 | grad norm: 0.263 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 907/ 3814 | consumed samples: 464384 | consumed tokens: 951058432 | elapsed time per iteration (s): 5.97 | learning rate: 4.883E-04 | global batch size: 512 | lm loss: 4.467900E+00 | loss scale: 8192.0 | grad norm: 0.197 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.723 | TFLOPs: 64.75 | +[default7]: iteration 908/ 3814 | consumed samples: 464896 | consumed tokens: 952107008 | elapsed time per iteration (s): 5.87 | learning rate: 4.882E-04 | global batch size: 512 | lm loss: 4.441376E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.174 | TFLOPs: 65.84 | +[default7]: iteration 909/ 3814 | consumed samples: 465408 | consumed tokens: 953155584 | elapsed time per iteration (s): 5.95 | learning rate: 4.880E-04 | global batch size: 512 | lm loss: 4.451180E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.981 | TFLOPs: 64.94 | +[default7]: iteration 910/ 3814 | consumed samples: 465920 | consumed tokens: 954204160 | elapsed time per iteration (s): 6.02 | learning rate: 4.879E-04 | global batch size: 512 | lm loss: 4.462988E+00 | loss scale: 8192.0 | grad norm: 0.325 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.039 | TFLOPs: 64.23 | +[default7]: iteration 911/ 3814 | consumed samples: 466432 | consumed tokens: 955252736 | elapsed time per iteration (s): 5.99 | learning rate: 4.878E-04 | global batch size: 512 | lm loss: 4.424294E+00 | loss scale: 8192.0 | grad norm: 0.309 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.508 | TFLOPs: 64.59 | +[default7]: iteration 912/ 3814 | consumed samples: 466944 | consumed tokens: 956301312 | elapsed time per iteration (s): 6.06 | learning rate: 4.877E-04 | global batch size: 512 | lm loss: 4.450391E+00 | loss scale: 8192.0 | grad norm: 0.211 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.556 | TFLOPs: 63.87 | +[default7]: iteration 913/ 3814 | consumed samples: 467456 | consumed tokens: 957349888 | elapsed time per iteration (s): 5.92 | learning rate: 4.876E-04 | global batch size: 512 | lm loss: 4.434988E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.535 | TFLOPs: 65.36 | +[default7]: iteration 914/ 3814 | consumed samples: 467968 | consumed tokens: 958398464 | elapsed time per iteration (s): 6.03 | learning rate: 4.875E-04 | global batch size: 512 | lm loss: 4.448422E+00 | loss scale: 8192.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.905 | TFLOPs: 64.13 | +[default7]: iteration 915/ 3814 | consumed samples: 468480 | consumed tokens: 959447040 | elapsed time per iteration (s): 5.97 | learning rate: 4.874E-04 | global batch size: 512 | lm loss: 4.460351E+00 | loss scale: 8192.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.806 | TFLOPs: 64.81 | +[default7]: iteration 916/ 3814 | consumed samples: 468992 | consumed tokens: 960495616 | elapsed time per iteration (s): 5.99 | learning rate: 4.872E-04 | global batch size: 512 | lm loss: 4.455590E+00 | loss scale: 8192.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.420 | TFLOPs: 64.52 | +[default7]: iteration 917/ 3814 | consumed samples: 469504 | consumed tokens: 961544192 | elapsed time per iteration (s): 5.99 | learning rate: 4.871E-04 | global batch size: 512 | lm loss: 4.431916E+00 | loss scale: 8192.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.530 | TFLOPs: 64.60 | +[default7]: iteration 918/ 3814 | consumed samples: 470016 | consumed tokens: 962592768 | elapsed time per iteration (s): 5.92 | learning rate: 4.870E-04 | global batch size: 512 | lm loss: 4.447072E+00 | loss scale: 8192.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.489 | TFLOPs: 65.33 | +[default7]: iteration 919/ 3814 | consumed samples: 470528 | consumed tokens: 963641344 | elapsed time per iteration (s): 5.94 | learning rate: 4.869E-04 | global batch size: 512 | lm loss: 4.411816E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.260 | TFLOPs: 65.15 | +[default7]: iteration 920/ 3814 | consumed samples: 471040 | consumed tokens: 964689920 | elapsed time per iteration (s): 5.95 | learning rate: 4.868E-04 | global batch size: 512 | lm loss: 4.417526E+00 | loss scale: 8192.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.067 | TFLOPs: 65.01 | +[default7]: iteration 921/ 3814 | consumed samples: 471552 | consumed tokens: 965738496 | elapsed time per iteration (s): 6.00 | learning rate: 4.867E-04 | global batch size: 512 | lm loss: 4.402958E+00 | loss scale: 8192.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.397 | TFLOPs: 64.50 | +[default7]: iteration 922/ 3814 | consumed samples: 472064 | consumed tokens: 966787072 | elapsed time per iteration (s): 5.95 | learning rate: 4.865E-04 | global batch size: 512 | lm loss: 4.401811E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.079 | TFLOPs: 65.02 | +[default7]: iteration 923/ 3814 | consumed samples: 472576 | consumed tokens: 967835648 | elapsed time per iteration (s): 5.96 | learning rate: 4.864E-04 | global batch size: 512 | lm loss: 4.423551E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.851 | TFLOPs: 64.84 | +[default7]: iteration 924/ 3814 | consumed samples: 473088 | consumed tokens: 968884224 | elapsed time per iteration (s): 5.99 | learning rate: 4.863E-04 | global batch size: 512 | lm loss: 4.402699E+00 | loss scale: 8192.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.526 | TFLOPs: 64.60 | +[default7]: iteration 925/ 3814 | consumed samples: 473600 | consumed tokens: 969932800 | elapsed time per iteration (s): 5.95 | learning rate: 4.862E-04 | global batch size: 512 | lm loss: 4.401243E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.119 | TFLOPs: 65.05 | +[default7]: iteration 926/ 3814 | consumed samples: 474112 | consumed tokens: 970981376 | elapsed time per iteration (s): 6.02 | learning rate: 4.861E-04 | global batch size: 512 | lm loss: 4.384336E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.115 | TFLOPs: 64.29 | +[default7]: iteration 927/ 3814 | consumed samples: 474624 | consumed tokens: 972029952 | elapsed time per iteration (s): 5.95 | learning rate: 4.860E-04 | global batch size: 512 | lm loss: 4.382324E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.047 | TFLOPs: 64.99 | +[default7]: iteration 928/ 3814 | consumed samples: 475136 | consumed tokens: 973078528 | elapsed time per iteration (s): 5.90 | learning rate: 4.858E-04 | global batch size: 512 | lm loss: 4.404491E+00 | loss scale: 8192.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.852 | TFLOPs: 65.60 | +[default7]: iteration 929/ 3814 | consumed samples: 475648 | consumed tokens: 974127104 | elapsed time per iteration (s): 5.98 | learning rate: 4.857E-04 | global batch size: 512 | lm loss: 4.404497E+00 | loss scale: 8192.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.650 | TFLOPs: 64.69 | +[default7]: iteration 930/ 3814 | consumed samples: 476160 | consumed tokens: 975175680 | elapsed time per iteration (s): 6.02 | learning rate: 4.856E-04 | global batch size: 512 | lm loss: 4.402380E+00 | loss scale: 8192.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.076 | TFLOPs: 64.26 | +[default7]: iteration 931/ 3814 | consumed samples: 476672 | consumed tokens: 976224256 | elapsed time per iteration (s): 6.00 | learning rate: 4.855E-04 | global batch size: 512 | lm loss: 4.375926E+00 | loss scale: 8192.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.373 | TFLOPs: 64.48 | +[default7]: iteration 932/ 3814 | consumed samples: 477184 | consumed tokens: 977272832 | elapsed time per iteration (s): 5.98 | learning rate: 4.854E-04 | global batch size: 512 | lm loss: 4.397953E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.684 | TFLOPs: 64.72 | +[default7]: iteration 933/ 3814 | consumed samples: 477696 | consumed tokens: 978321408 | elapsed time per iteration (s): 6.00 | learning rate: 4.853E-04 | global batch size: 512 | lm loss: 4.377647E+00 | loss scale: 8192.0 | grad norm: 0.237 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.340 | TFLOPs: 64.46 | +[default7]: iteration 934/ 3814 | consumed samples: 478208 | consumed tokens: 979369984 | elapsed time per iteration (s): 5.96 | learning rate: 4.851E-04 | global batch size: 512 | lm loss: 4.362362E+00 | loss scale: 8192.0 | grad norm: 0.275 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.959 | TFLOPs: 64.93 | +[default7]: iteration 935/ 3814 | consumed samples: 478720 | consumed tokens: 980418560 | elapsed time per iteration (s): 5.95 | learning rate: 4.850E-04 | global batch size: 512 | lm loss: 4.395741E+00 | loss scale: 8192.0 | grad norm: 0.269 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.064 | TFLOPs: 65.00 | +[default7]: iteration 936/ 3814 | consumed samples: 479232 | consumed tokens: 981467136 | elapsed time per iteration (s): 5.82 | learning rate: 4.849E-04 | global batch size: 512 | lm loss: 4.379987E+00 | loss scale: 8192.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.034 | TFLOPs: 66.49 | +[default7]: iteration 937/ 3814 | consumed samples: 479744 | consumed tokens: 982515712 | elapsed time per iteration (s): 5.98 | learning rate: 4.848E-04 | global batch size: 512 | lm loss: 4.415142E+00 | loss scale: 8192.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.628 | TFLOPs: 64.68 | +[default7]: iteration 938/ 3814 | consumed samples: 480256 | consumed tokens: 983564288 | elapsed time per iteration (s): 5.97 | learning rate: 4.847E-04 | global batch size: 512 | lm loss: 4.377728E+00 | loss scale: 8192.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.748 | TFLOPs: 64.77 | +[default7]: iteration 939/ 3814 | consumed samples: 480768 | consumed tokens: 984612864 | elapsed time per iteration (s): 5.92 | learning rate: 4.846E-04 | global batch size: 512 | lm loss: 4.391349E+00 | loss scale: 8192.0 | grad norm: 0.337 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.541 | TFLOPs: 65.36 | +[default7]: iteration 940/ 3814 | consumed samples: 481280 | consumed tokens: 985661440 | elapsed time per iteration (s): 6.03 | learning rate: 4.844E-04 | global batch size: 512 | lm loss: 4.402933E+00 | loss scale: 8192.0 | grad norm: 0.324 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.978 | TFLOPs: 64.18 | +[default7]: iteration 941/ 3814 | consumed samples: 481792 | consumed tokens: 986710016 | elapsed time per iteration (s): 5.97 | learning rate: 4.843E-04 | global batch size: 512 | lm loss: 4.395652E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.746 | TFLOPs: 64.76 | +[default7]: iteration 942/ 3814 | consumed samples: 482304 | consumed tokens: 987758592 | elapsed time per iteration (s): 6.01 | learning rate: 4.842E-04 | global batch size: 512 | lm loss: 4.360468E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.133 | TFLOPs: 64.30 | +[default7]: iteration 943/ 3814 | consumed samples: 482816 | consumed tokens: 988807168 | elapsed time per iteration (s): 5.90 | learning rate: 4.841E-04 | global batch size: 512 | lm loss: 4.390438E+00 | loss scale: 8192.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.810 | TFLOPs: 65.57 | +[default7]: iteration 944/ 3814 | consumed samples: 483328 | consumed tokens: 989855744 | elapsed time per iteration (s): 5.97 | learning rate: 4.840E-04 | global batch size: 512 | lm loss: 4.347669E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.744 | TFLOPs: 64.76 | +[default7]: iteration 945/ 3814 | consumed samples: 483840 | consumed tokens: 990904320 | elapsed time per iteration (s): 5.99 | learning rate: 4.838E-04 | global batch size: 512 | lm loss: 4.389667E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.425 | TFLOPs: 64.52 | +[default7]: iteration 946/ 3814 | consumed samples: 484352 | consumed tokens: 991952896 | elapsed time per iteration (s): 5.95 | learning rate: 4.837E-04 | global batch size: 512 | lm loss: 4.361993E+00 | loss scale: 8192.0 | grad norm: 0.225 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.041 | TFLOPs: 64.99 | +[default7]: iteration 947/ 3814 | consumed samples: 484864 | consumed tokens: 993001472 | elapsed time per iteration (s): 5.89 | learning rate: 4.836E-04 | global batch size: 512 | lm loss: 4.359410E+00 | loss scale: 8192.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.926 | TFLOPs: 65.66 | +[default7]: iteration 948/ 3814 | consumed samples: 485376 | consumed tokens: 994050048 | elapsed time per iteration (s): 5.90 | learning rate: 4.835E-04 | global batch size: 512 | lm loss: 4.360261E+00 | loss scale: 8192.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.784 | TFLOPs: 65.55 | +[default7]: iteration 949/ 3814 | consumed samples: 485888 | consumed tokens: 995098624 | elapsed time per iteration (s): 5.97 | learning rate: 4.834E-04 | global batch size: 512 | lm loss: 4.365931E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.742 | TFLOPs: 64.76 | +[default7]: iteration 950/ 3814 | consumed samples: 486400 | consumed tokens: 996147200 | elapsed time per iteration (s): 5.99 | learning rate: 4.832E-04 | global batch size: 512 | lm loss: 4.379857E+00 | loss scale: 8192.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.478 | TFLOPs: 64.56 | +[default7]: iteration 951/ 3814 | consumed samples: 486912 | consumed tokens: 997195776 | elapsed time per iteration (s): 5.96 | learning rate: 4.831E-04 | global batch size: 512 | lm loss: 4.343833E+00 | loss scale: 8192.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.964 | TFLOPs: 64.93 | +[default7]: iteration 952/ 3814 | consumed samples: 487424 | consumed tokens: 998244352 | elapsed time per iteration (s): 5.93 | learning rate: 4.830E-04 | global batch size: 512 | lm loss: 4.361631E+00 | loss scale: 8192.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.348 | TFLOPs: 65.22 | +[default7]: iteration 953/ 3814 | consumed samples: 487936 | consumed tokens: 999292928 | elapsed time per iteration (s): 5.98 | learning rate: 4.829E-04 | global batch size: 512 | lm loss: 4.338993E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.674 | TFLOPs: 64.71 | +[default7]: iteration 954/ 3814 | consumed samples: 488448 | consumed tokens: 1000341504 | elapsed time per iteration (s): 6.03 | learning rate: 4.827E-04 | global batch size: 512 | lm loss: 4.343524E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.950 | TFLOPs: 64.16 | +[default7]: iteration 955/ 3814 | consumed samples: 488960 | consumed tokens: 1001390080 | elapsed time per iteration (s): 5.64 | learning rate: 4.826E-04 | global batch size: 512 | lm loss: 4.324158E+00 | loss scale: 8192.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.736 | TFLOPs: 68.53 | +[default7]: iteration 956/ 3814 | consumed samples: 489472 | consumed tokens: 1002438656 | elapsed time per iteration (s): 5.99 | learning rate: 4.825E-04 | global batch size: 512 | lm loss: 4.333399E+00 | loss scale: 8192.0 | grad norm: 0.209 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.515 | TFLOPs: 64.59 | +[default7]: iteration 957/ 3814 | consumed samples: 489984 | consumed tokens: 1003487232 | elapsed time per iteration (s): 6.00 | learning rate: 4.824E-04 | global batch size: 512 | lm loss: 4.330816E+00 | loss scale: 8192.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.358 | TFLOPs: 64.47 | +[default7]: iteration 958/ 3814 | consumed samples: 490496 | consumed tokens: 1004535808 | elapsed time per iteration (s): 5.96 | learning rate: 4.823E-04 | global batch size: 512 | lm loss: 4.343353E+00 | loss scale: 8192.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.892 | TFLOPs: 64.88 | +[default7]: iteration 959/ 3814 | consumed samples: 491008 | consumed tokens: 1005584384 | elapsed time per iteration (s): 5.98 | learning rate: 4.821E-04 | global batch size: 512 | lm loss: 4.355972E+00 | loss scale: 8192.0 | grad norm: 0.297 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.667 | TFLOPs: 64.71 | +[default7]: iteration 960/ 3814 | consumed samples: 491520 | consumed tokens: 1006632960 | elapsed time per iteration (s): 5.87 | learning rate: 4.820E-04 | global batch size: 512 | lm loss: 4.356530E+00 | loss scale: 8192.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.201 | TFLOPs: 65.86 | +[default7]: iteration 961/ 3814 | consumed samples: 492032 | consumed tokens: 1007681536 | elapsed time per iteration (s): 5.99 | learning rate: 4.819E-04 | global batch size: 512 | lm loss: 4.334553E+00 | loss scale: 8192.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.424 | TFLOPs: 64.52 | +[default7]: iteration 962/ 3814 | consumed samples: 492544 | consumed tokens: 1008730112 | elapsed time per iteration (s): 5.95 | learning rate: 4.818E-04 | global batch size: 512 | lm loss: 4.348050E+00 | loss scale: 8192.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.092 | TFLOPs: 65.03 | +[default7]: iteration 963/ 3814 | consumed samples: 493056 | consumed tokens: 1009778688 | elapsed time per iteration (s): 5.96 | learning rate: 4.816E-04 | global batch size: 512 | lm loss: 4.329963E+00 | loss scale: 8192.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.914 | TFLOPs: 64.89 | +[default7]: iteration 964/ 3814 | consumed samples: 493568 | consumed tokens: 1010827264 | elapsed time per iteration (s): 5.98 | learning rate: 4.815E-04 | global batch size: 512 | lm loss: 4.350635E+00 | loss scale: 8192.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.589 | TFLOPs: 64.65 | +[default7]: iteration 965/ 3814 | consumed samples: 494080 | consumed tokens: 1011875840 | elapsed time per iteration (s): 5.97 | learning rate: 4.814E-04 | global batch size: 512 | lm loss: 4.335535E+00 | loss scale: 8192.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.800 | TFLOPs: 64.81 | +[default7]: iteration 966/ 3814 | consumed samples: 494592 | consumed tokens: 1012924416 | elapsed time per iteration (s): 5.84 | learning rate: 4.813E-04 | global batch size: 512 | lm loss: 4.334705E+00 | loss scale: 8192.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.649 | TFLOPs: 66.20 | +[default7]: iteration 967/ 3814 | consumed samples: 495104 | consumed tokens: 1013972992 | elapsed time per iteration (s): 5.99 | learning rate: 4.811E-04 | global batch size: 512 | lm loss: 4.311568E+00 | loss scale: 8192.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.543 | TFLOPs: 64.61 | +[default7]: iteration 968/ 3814 | consumed samples: 495616 | consumed tokens: 1015021568 | elapsed time per iteration (s): 5.96 | learning rate: 4.810E-04 | global batch size: 512 | lm loss: 4.306081E+00 | loss scale: 8192.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.923 | TFLOPs: 64.90 | +[default7]: iteration 969/ 3814 | consumed samples: 496128 | consumed tokens: 1016070144 | elapsed time per iteration (s): 5.98 | learning rate: 4.809E-04 | global batch size: 512 | lm loss: 4.307449E+00 | loss scale: 8192.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.662 | TFLOPs: 64.70 | +[default7]: iteration 970/ 3814 | consumed samples: 496640 | consumed tokens: 1017118720 | elapsed time per iteration (s): 5.90 | learning rate: 4.808E-04 | global batch size: 512 | lm loss: 4.316981E+00 | loss scale: 8192.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.753 | TFLOPs: 65.53 | +[default7]: iteration 971/ 3814 | consumed samples: 497152 | consumed tokens: 1018167296 | elapsed time per iteration (s): 5.97 | learning rate: 4.806E-04 | global batch size: 512 | lm loss: 4.321224E+00 | loss scale: 8192.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.786 | TFLOPs: 64.80 | +[default7]: iteration 972/ 3814 | consumed samples: 497664 | consumed tokens: 1019215872 | elapsed time per iteration (s): 5.93 | learning rate: 4.805E-04 | global batch size: 512 | lm loss: 4.321185E+00 | loss scale: 8192.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.314 | TFLOPs: 65.19 | +[default7]: iteration 973/ 3814 | consumed samples: 498176 | consumed tokens: 1020264448 | elapsed time per iteration (s): 6.00 | learning rate: 4.804E-04 | global batch size: 512 | lm loss: 4.293108E+00 | loss scale: 8192.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.303 | TFLOPs: 64.43 | +[default7]: iteration 974/ 3814 | consumed samples: 498688 | consumed tokens: 1021313024 | elapsed time per iteration (s): 5.94 | learning rate: 4.803E-04 | global batch size: 512 | lm loss: 4.313969E+00 | loss scale: 8192.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.169 | TFLOPs: 65.08 | +[default7]: iteration 975/ 3814 | consumed samples: 499200 | consumed tokens: 1022361600 | elapsed time per iteration (s): 6.07 | learning rate: 4.801E-04 | global batch size: 512 | lm loss: 4.315232E+00 | loss scale: 8192.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.298 | TFLOPs: 63.67 | +[default7]: iteration 976/ 3814 | consumed samples: 499712 | consumed tokens: 1023410176 | elapsed time per iteration (s): 5.87 | learning rate: 4.800E-04 | global batch size: 512 | lm loss: 4.330128E+00 | loss scale: 8192.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.252 | TFLOPs: 65.90 | +[default7]: iteration 977/ 3814 | consumed samples: 500224 | consumed tokens: 1024458752 | elapsed time per iteration (s): 6.02 | learning rate: 4.799E-04 | global batch size: 512 | lm loss: 4.316091E+00 | loss scale: 8192.0 | grad norm: 0.234 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.107 | TFLOPs: 64.28 | +[default7]: iteration 978/ 3814 | consumed samples: 500736 | consumed tokens: 1025507328 | elapsed time per iteration (s): 6.00 | learning rate: 4.798E-04 | global batch size: 512 | lm loss: 4.313098E+00 | loss scale: 8192.0 | grad norm: 0.243 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.385 | TFLOPs: 64.49 | +[default7]: iteration 979/ 3814 | consumed samples: 501248 | consumed tokens: 1026555904 | elapsed time per iteration (s): 6.01 | learning rate: 4.796E-04 | global batch size: 512 | lm loss: 4.307465E+00 | loss scale: 8192.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.136 | TFLOPs: 64.30 | +[default7]: iteration 980/ 3814 | consumed samples: 501760 | consumed tokens: 1027604480 | elapsed time per iteration (s): 5.94 | learning rate: 4.795E-04 | global batch size: 512 | lm loss: 4.300125E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.125 | TFLOPs: 65.05 | +[default7]: iteration 981/ 3814 | consumed samples: 502272 | consumed tokens: 1028653056 | elapsed time per iteration (s): 5.93 | learning rate: 4.794E-04 | global batch size: 512 | lm loss: 4.286670E+00 | loss scale: 8192.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.318 | TFLOPs: 65.20 | +[default7]: iteration 982/ 3814 | consumed samples: 502784 | consumed tokens: 1029701632 | elapsed time per iteration (s): 5.86 | learning rate: 4.793E-04 | global batch size: 512 | lm loss: 4.310596E+00 | loss scale: 8192.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.371 | TFLOPs: 65.99 | +[default7]: iteration 983/ 3814 | consumed samples: 503296 | consumed tokens: 1030750208 | elapsed time per iteration (s): 5.97 | learning rate: 4.791E-04 | global batch size: 512 | lm loss: 4.320741E+00 | loss scale: 8192.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.750 | TFLOPs: 64.77 | +[default7]: iteration 984/ 3814 | consumed samples: 503808 | consumed tokens: 1031798784 | elapsed time per iteration (s): 5.97 | learning rate: 4.790E-04 | global batch size: 512 | lm loss: 4.278260E+00 | loss scale: 8192.0 | grad norm: 0.242 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.828 | TFLOPs: 64.83 | +[default7]: iteration 985/ 3814 | consumed samples: 504320 | consumed tokens: 1032847360 | elapsed time per iteration (s): 5.96 | learning rate: 4.789E-04 | global batch size: 512 | lm loss: 4.339976E+00 | loss scale: 8192.0 | grad norm: 0.259 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.856 | TFLOPs: 64.85 | +[default7]: iteration 986/ 3814 | consumed samples: 504832 | consumed tokens: 1033895936 | elapsed time per iteration (s): 5.97 | learning rate: 4.787E-04 | global batch size: 512 | lm loss: 4.300331E+00 | loss scale: 8192.0 | grad norm: 0.271 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.792 | TFLOPs: 64.80 | +[default7]: iteration 987/ 3814 | consumed samples: 505344 | consumed tokens: 1034944512 | elapsed time per iteration (s): 5.93 | learning rate: 4.786E-04 | global batch size: 512 | lm loss: 4.313455E+00 | loss scale: 8192.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.341 | TFLOPs: 65.21 | +[default7]: iteration 988/ 3814 | consumed samples: 505856 | consumed tokens: 1035993088 | elapsed time per iteration (s): 6.00 | learning rate: 4.785E-04 | global batch size: 512 | lm loss: 4.307003E+00 | loss scale: 8192.0 | grad norm: 0.219 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.360 | TFLOPs: 64.47 | +[default7]: iteration 989/ 3814 | consumed samples: 506368 | consumed tokens: 1037041664 | elapsed time per iteration (s): 5.98 | learning rate: 4.784E-04 | global batch size: 512 | lm loss: 4.316042E+00 | loss scale: 8192.0 | grad norm: 0.227 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.558 | TFLOPs: 64.62 | +[default7]: iteration 990/ 3814 | consumed samples: 506880 | consumed tokens: 1038090240 | elapsed time per iteration (s): 6.00 | learning rate: 4.782E-04 | global batch size: 512 | lm loss: 4.331728E+00 | loss scale: 8192.0 | grad norm: 0.215 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.277 | TFLOPs: 64.41 | +[default7]: iteration 991/ 3814 | consumed samples: 507392 | consumed tokens: 1039138816 | elapsed time per iteration (s): 6.00 | learning rate: 4.781E-04 | global batch size: 512 | lm loss: 4.295420E+00 | loss scale: 8192.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.326 | TFLOPs: 64.45 | +[default7]: iteration 992/ 3814 | consumed samples: 507904 | consumed tokens: 1040187392 | elapsed time per iteration (s): 5.95 | learning rate: 4.780E-04 | global batch size: 512 | lm loss: 4.267017E+00 | loss scale: 8192.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.047 | TFLOPs: 64.99 | +[default7]: iteration 993/ 3814 | consumed samples: 508416 | consumed tokens: 1041235968 | elapsed time per iteration (s): 6.02 | learning rate: 4.779E-04 | global batch size: 512 | lm loss: 4.274907E+00 | loss scale: 8192.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.015 | TFLOPs: 64.21 | +[default7]: iteration 994/ 3814 | consumed samples: 508928 | consumed tokens: 1042284544 | elapsed time per iteration (s): 6.02 | learning rate: 4.777E-04 | global batch size: 512 | lm loss: 4.298199E+00 | loss scale: 8192.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.080 | TFLOPs: 64.26 | +[default7]: iteration 995/ 3814 | consumed samples: 509440 | consumed tokens: 1043333120 | elapsed time per iteration (s): 5.94 | learning rate: 4.776E-04 | global batch size: 512 | lm loss: 4.288421E+00 | loss scale: 8192.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.130 | TFLOPs: 65.05 | +[default7]: iteration 996/ 3814 | consumed samples: 509952 | consumed tokens: 1044381696 | elapsed time per iteration (s): 5.98 | learning rate: 4.775E-04 | global batch size: 512 | lm loss: 4.237576E+00 | loss scale: 8192.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.672 | TFLOPs: 64.71 | +[default7]: iteration 997/ 3814 | consumed samples: 510464 | consumed tokens: 1045430272 | elapsed time per iteration (s): 5.89 | learning rate: 4.773E-04 | global batch size: 512 | lm loss: 4.260945E+00 | loss scale: 8192.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.887 | TFLOPs: 65.63 | +[default7]: iteration 998/ 3814 | consumed samples: 510976 | consumed tokens: 1046478848 | elapsed time per iteration (s): 5.98 | learning rate: 4.772E-04 | global batch size: 512 | lm loss: 4.295516E+00 | loss scale: 8192.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.581 | TFLOPs: 64.64 | +[default7]: iteration 999/ 3814 | consumed samples: 511488 | consumed tokens: 1047527424 | elapsed time per iteration (s): 6.03 | learning rate: 4.771E-04 | global batch size: 512 | lm loss: 4.255163E+00 | loss scale: 8192.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.904 | TFLOPs: 64.13 | +[default7]: iteration 1000/ 3814 | consumed samples: 512000 | consumed tokens: 1048576000 | elapsed time per iteration (s): 5.95 | learning rate: 4.769E-04 | global batch size: 512 | lm loss: 4.280150E+00 | loss scale: 16384.0 | grad norm: 0.084 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.000 | TFLOPs: 64.96 | +[default1]:[2023-02-16 09:12:16,701] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 1000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 09:12:16,698] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1000 is begin to save! +[default0]:[2023-02-16 09:12:16,701] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_00-model_states.pt... +[default7]:------------------------------------------------------------------------------------------ +[default7]:valid loss at iteration 1000 | lm loss value: 4.216615E+00 | lm loss PPL: 6.780356E+01 | +[default7]:------------------------------------------------------------------------------------------ +[default1]:[2023-02-16 09:12:16,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:16,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:16,882] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:16,882] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:16,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:16,939] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:17,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,000] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:16,966] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:16,966] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:17,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,032] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,064] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:17,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,188] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,158] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:17,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,222] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:17,317] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,317] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,284] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:17,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,348] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,411] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,412] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,442] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:17,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,504] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:17,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,537] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,568] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:17,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,631] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,602] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,697] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:17,738] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,738] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:17,836] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,837] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,803] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,803] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,898] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,898] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,865] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,865] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:17,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,930] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:17,959] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:17,960] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,025] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:17,993] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:17,993] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,086] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,087] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,056] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:18,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,119] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,147] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,207] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,207] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:18,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,271] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,317] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,400] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,388] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:18,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,460] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,522] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,516] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,588] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:18,644] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,645] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,648] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,718] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,783] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 09:12:18,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,788] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:18,850] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,851] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 09:12:18,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,905] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 09:12:18,905] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 09:12:18,907] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_01_model_states.pt +[default1]:[2023-02-16 09:12:18,907] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 09:12:18,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 09:12:18,912] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_00-model_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:12:18,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 09:12:18,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 09:12:18,978] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_00_model_states.pt +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:12:18,978] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 09:12:18,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:12:19,007] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:12:19,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,467] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,500] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,501] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,501] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,603] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,599] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,623] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,623] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,613] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,615] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,642] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,642] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,642] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,623] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,623] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,633] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,633] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,633] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,654] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,654] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,606] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,602] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,603] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,613] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,613] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,613] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,664] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,665] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,657] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,657] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,657] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,662] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,632] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,632] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,632] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 09:12:19,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,653] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,653] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,685] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,685] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,683] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,660] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,660] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,660] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,718] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 09:12:19,663] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,663] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,663] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,721] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,721] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,723] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,723] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,723] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,651] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,651] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,689] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,714] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,714] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,715] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,753] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,753] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,754] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,707] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,709] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,709] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,675] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,725] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 09:12:19,735] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,735] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,735] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,696] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,696] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,696] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,684] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,684] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,684] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 09:12:19,680] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,680] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,680] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,689] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,732] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,752] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,687] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,719] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 09:12:19,766] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,766] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,767] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,740] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,740] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,740] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,730] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,789] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,789] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,746] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,747] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,833] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,833] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,764] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,796] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,796] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,796] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default4]:[2023-02-16 09:12:19,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:12:19,784] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:12:19,784] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default2]:[2023-02-16 09:12:19,790] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:12:19,790] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:12:19,790] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,804] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,805] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,805] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:[2023-02-16 09:12:19,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,794] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,794] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default1]:[2023-02-16 09:12:19,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:12:19,802] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:12:19,802] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default5]:[2023-02-16 09:12:19,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:12:19,820] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:12:19,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]:[2023-02-16 09:12:19,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:12:19,821] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:12:19,821] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default3]:[2023-02-16 09:12:19,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:12:19,813] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:12:19,813] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,846] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,846] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,846] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default0]: successfully saved checkpoint at iteration 1000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:[2023-02-16 09:12:19,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,887] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default6]:[2023-02-16 09:12:19,918] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:12:19,918] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:12:19,918] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]:time (ms) | save-checkpoint: 3221.84 +[default7]:[2023-02-16 09:12:19,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:12:19,917] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1000/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:12:19,917] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1000 is ready now! +[default7]: iteration 1001/ 3814 | consumed samples: 512512 | consumed tokens: 1049624576 | elapsed time per iteration (s): 10.28 | learning rate: 4.768E-04 | global batch size: 512 | lm loss: 4.290764E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 49.827 | TFLOPs: 37.63 | +[default7]: iteration 1002/ 3814 | consumed samples: 513024 | consumed tokens: 1050673152 | elapsed time per iteration (s): 5.98 | learning rate: 4.767E-04 | global batch size: 512 | lm loss: 4.305445E+00 | loss scale: 16384.0 | grad norm: 0.221 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.668 | TFLOPs: 64.71 | +[default7]: iteration 1003/ 3814 | consumed samples: 513536 | consumed tokens: 1051721728 | elapsed time per iteration (s): 5.99 | learning rate: 4.766E-04 | global batch size: 512 | lm loss: 4.243632E+00 | loss scale: 16384.0 | grad norm: 0.230 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.505 | TFLOPs: 64.58 | +[default7]: iteration 1004/ 3814 | consumed samples: 514048 | consumed tokens: 1052770304 | elapsed time per iteration (s): 6.03 | learning rate: 4.764E-04 | global batch size: 512 | lm loss: 4.267708E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.939 | TFLOPs: 64.16 | +[default7]: iteration 1005/ 3814 | consumed samples: 514560 | consumed tokens: 1053818880 | elapsed time per iteration (s): 5.99 | learning rate: 4.763E-04 | global batch size: 512 | lm loss: 4.254086E+00 | loss scale: 16384.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.526 | TFLOPs: 64.60 | +[default7]: iteration 1006/ 3814 | consumed samples: 515072 | consumed tokens: 1054867456 | elapsed time per iteration (s): 5.95 | learning rate: 4.762E-04 | global batch size: 512 | lm loss: 4.294357E+00 | loss scale: 16384.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.014 | TFLOPs: 64.97 | +[default7]: iteration 1007/ 3814 | consumed samples: 515584 | consumed tokens: 1055916032 | elapsed time per iteration (s): 6.00 | learning rate: 4.760E-04 | global batch size: 512 | lm loss: 4.253786E+00 | loss scale: 16384.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.348 | TFLOPs: 64.46 | +[default7]: iteration 1008/ 3814 | consumed samples: 516096 | consumed tokens: 1056964608 | elapsed time per iteration (s): 6.02 | learning rate: 4.759E-04 | global batch size: 512 | lm loss: 4.247293E+00 | loss scale: 16384.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.020 | TFLOPs: 64.22 | +[default7]: iteration 1009/ 3814 | consumed samples: 516608 | consumed tokens: 1058013184 | elapsed time per iteration (s): 6.02 | learning rate: 4.758E-04 | global batch size: 512 | lm loss: 4.253902E+00 | loss scale: 16384.0 | grad norm: 0.216 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.059 | TFLOPs: 64.25 | +[default7]: iteration 1010/ 3814 | consumed samples: 517120 | consumed tokens: 1059061760 | elapsed time per iteration (s): 6.04 | learning rate: 4.756E-04 | global batch size: 512 | lm loss: 4.285875E+00 | loss scale: 16384.0 | grad norm: 0.238 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.770 | TFLOPs: 64.03 | +[default7]: iteration 1011/ 3814 | consumed samples: 517632 | consumed tokens: 1060110336 | elapsed time per iteration (s): 6.11 | learning rate: 4.755E-04 | global batch size: 512 | lm loss: 4.253871E+00 | loss scale: 16384.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.815 | TFLOPs: 63.31 | +[default7]: iteration 1012/ 3814 | consumed samples: 518144 | consumed tokens: 1061158912 | elapsed time per iteration (s): 5.62 | learning rate: 4.754E-04 | global batch size: 512 | lm loss: 4.224390E+00 | loss scale: 16384.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 91.159 | TFLOPs: 68.85 | +[default7]: iteration 1013/ 3814 | consumed samples: 518656 | consumed tokens: 1062207488 | elapsed time per iteration (s): 6.05 | learning rate: 4.752E-04 | global batch size: 512 | lm loss: 4.232445E+00 | loss scale: 16384.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.627 | TFLOPs: 63.92 | +[default7]: iteration 1014/ 3814 | consumed samples: 519168 | consumed tokens: 1063256064 | elapsed time per iteration (s): 6.01 | learning rate: 4.751E-04 | global batch size: 512 | lm loss: 4.241261E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.177 | TFLOPs: 64.33 | +[default7]: iteration 1015/ 3814 | consumed samples: 519680 | consumed tokens: 1064304640 | elapsed time per iteration (s): 6.01 | learning rate: 4.750E-04 | global batch size: 512 | lm loss: 4.237112E+00 | loss scale: 16384.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.147 | TFLOPs: 64.31 | +[default7]: iteration 1016/ 3814 | consumed samples: 520192 | consumed tokens: 1065353216 | elapsed time per iteration (s): 6.05 | learning rate: 4.748E-04 | global batch size: 512 | lm loss: 4.236486E+00 | loss scale: 16384.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.577 | TFLOPs: 63.88 | +[default7]: iteration 1017/ 3814 | consumed samples: 520704 | consumed tokens: 1066401792 | elapsed time per iteration (s): 6.03 | learning rate: 4.747E-04 | global batch size: 512 | lm loss: 4.230018E+00 | loss scale: 16384.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.853 | TFLOPs: 64.09 | +[default7]: iteration 1018/ 3814 | consumed samples: 521216 | consumed tokens: 1067450368 | elapsed time per iteration (s): 6.05 | learning rate: 4.746E-04 | global batch size: 512 | lm loss: 4.222076E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.696 | TFLOPs: 63.97 | +[default7]: iteration 1019/ 3814 | consumed samples: 521728 | consumed tokens: 1068498944 | elapsed time per iteration (s): 5.96 | learning rate: 4.744E-04 | global batch size: 512 | lm loss: 4.248742E+00 | loss scale: 16384.0 | grad norm: 0.232 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.946 | TFLOPs: 64.92 | +[default7]: iteration 1020/ 3814 | consumed samples: 522240 | consumed tokens: 1069547520 | elapsed time per iteration (s): 6.06 | learning rate: 4.743E-04 | global batch size: 512 | lm loss: 4.248693E+00 | loss scale: 16384.0 | grad norm: 0.220 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.489 | TFLOPs: 63.82 | +[default7]: iteration 1021/ 3814 | consumed samples: 522752 | consumed tokens: 1070596096 | elapsed time per iteration (s): 6.05 | learning rate: 4.742E-04 | global batch size: 512 | lm loss: 4.254896E+00 | loss scale: 16384.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.573 | TFLOPs: 63.88 | +[default7]: iteration 1022/ 3814 | consumed samples: 523264 | consumed tokens: 1071644672 | elapsed time per iteration (s): 5.96 | learning rate: 4.740E-04 | global batch size: 512 | lm loss: 4.234431E+00 | loss scale: 16384.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.912 | TFLOPs: 64.89 | +[default7]: iteration 1023/ 3814 | consumed samples: 523776 | consumed tokens: 1072693248 | elapsed time per iteration (s): 6.04 | learning rate: 4.739E-04 | global batch size: 512 | lm loss: 4.213659E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.712 | TFLOPs: 63.98 | +[default7]: iteration 1024/ 3814 | consumed samples: 524288 | consumed tokens: 1073741824 | elapsed time per iteration (s): 6.03 | learning rate: 4.738E-04 | global batch size: 512 | lm loss: 4.225054E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.853 | TFLOPs: 64.09 | +[default7]: iteration 1025/ 3814 | consumed samples: 524800 | consumed tokens: 1074790400 | elapsed time per iteration (s): 6.06 | learning rate: 4.736E-04 | global batch size: 512 | lm loss: 4.237177E+00 | loss scale: 16384.0 | grad norm: 0.193 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.490 | TFLOPs: 63.82 | +[default7]: iteration 1026/ 3814 | consumed samples: 525312 | consumed tokens: 1075838976 | elapsed time per iteration (s): 6.07 | learning rate: 4.735E-04 | global batch size: 512 | lm loss: 4.210115E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.371 | TFLOPs: 63.73 | +[default7]: iteration 1027/ 3814 | consumed samples: 525824 | consumed tokens: 1076887552 | elapsed time per iteration (s): 6.05 | learning rate: 4.734E-04 | global batch size: 512 | lm loss: 4.218585E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.641 | TFLOPs: 63.93 | +[default7]: iteration 1028/ 3814 | consumed samples: 526336 | consumed tokens: 1077936128 | elapsed time per iteration (s): 6.05 | learning rate: 4.732E-04 | global batch size: 512 | lm loss: 4.229543E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.559 | TFLOPs: 63.87 | +[default7]: iteration 1029/ 3814 | consumed samples: 526848 | consumed tokens: 1078984704 | elapsed time per iteration (s): 6.03 | learning rate: 4.731E-04 | global batch size: 512 | lm loss: 4.227538E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.937 | TFLOPs: 64.15 | +[default7]: iteration 1030/ 3814 | consumed samples: 527360 | consumed tokens: 1080033280 | elapsed time per iteration (s): 6.05 | learning rate: 4.730E-04 | global batch size: 512 | lm loss: 4.191898E+00 | loss scale: 16384.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.688 | TFLOPs: 63.97 | +[default7]: iteration 1031/ 3814 | consumed samples: 527872 | consumed tokens: 1081081856 | elapsed time per iteration (s): 6.09 | learning rate: 4.728E-04 | global batch size: 512 | lm loss: 4.232298E+00 | loss scale: 16384.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.136 | TFLOPs: 63.55 | +[default7]: iteration 1032/ 3814 | consumed samples: 528384 | consumed tokens: 1082130432 | elapsed time per iteration (s): 6.00 | learning rate: 4.727E-04 | global batch size: 512 | lm loss: 4.211709E+00 | loss scale: 16384.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.379 | TFLOPs: 64.49 | +[default7]: iteration 1033/ 3814 | consumed samples: 528896 | consumed tokens: 1083179008 | elapsed time per iteration (s): 6.09 | learning rate: 4.725E-04 | global batch size: 512 | lm loss: 4.206371E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.032 | TFLOPs: 63.47 | +[default7]: iteration 1034/ 3814 | consumed samples: 529408 | consumed tokens: 1084227584 | elapsed time per iteration (s): 5.84 | learning rate: 4.724E-04 | global batch size: 512 | lm loss: 4.256962E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.645 | TFLOPs: 66.20 | +[default7]: iteration 1035/ 3814 | consumed samples: 529920 | consumed tokens: 1085276160 | elapsed time per iteration (s): 5.95 | learning rate: 4.723E-04 | global batch size: 512 | lm loss: 4.216681E+00 | loss scale: 16384.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.991 | TFLOPs: 64.95 | +[default7]: iteration 1036/ 3814 | consumed samples: 530432 | consumed tokens: 1086324736 | elapsed time per iteration (s): 6.04 | learning rate: 4.721E-04 | global batch size: 512 | lm loss: 4.203806E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.797 | TFLOPs: 64.05 | +[default7]: iteration 1037/ 3814 | consumed samples: 530944 | consumed tokens: 1087373312 | elapsed time per iteration (s): 6.04 | learning rate: 4.720E-04 | global batch size: 512 | lm loss: 4.183322E+00 | loss scale: 16384.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.818 | TFLOPs: 64.06 | +[default7]: iteration 1038/ 3814 | consumed samples: 531456 | consumed tokens: 1088421888 | elapsed time per iteration (s): 6.06 | learning rate: 4.719E-04 | global batch size: 512 | lm loss: 4.242588E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.444 | TFLOPs: 63.78 | +[default7]: iteration 1039/ 3814 | consumed samples: 531968 | consumed tokens: 1089470464 | elapsed time per iteration (s): 6.06 | learning rate: 4.717E-04 | global batch size: 512 | lm loss: 4.196122E+00 | loss scale: 16384.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.438 | TFLOPs: 63.78 | +[default7]: iteration 1040/ 3814 | consumed samples: 532480 | consumed tokens: 1090519040 | elapsed time per iteration (s): 6.05 | learning rate: 4.716E-04 | global batch size: 512 | lm loss: 4.188737E+00 | loss scale: 16384.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.563 | TFLOPs: 63.87 | +[default7]: iteration 1041/ 3814 | consumed samples: 532992 | consumed tokens: 1091567616 | elapsed time per iteration (s): 6.05 | learning rate: 4.715E-04 | global batch size: 512 | lm loss: 4.188354E+00 | loss scale: 16384.0 | grad norm: 0.253 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.609 | TFLOPs: 63.91 | +[default7]: iteration 1042/ 3814 | consumed samples: 533504 | consumed tokens: 1092616192 | elapsed time per iteration (s): 6.02 | learning rate: 4.713E-04 | global batch size: 512 | lm loss: 4.212331E+00 | loss scale: 16384.0 | grad norm: 0.223 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.078 | TFLOPs: 64.26 | +[default7]: iteration 1043/ 3814 | consumed samples: 534016 | consumed tokens: 1093664768 | elapsed time per iteration (s): 5.99 | learning rate: 4.712E-04 | global batch size: 512 | lm loss: 4.201474E+00 | loss scale: 16384.0 | grad norm: 0.212 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.495 | TFLOPs: 64.57 | +[default7]: iteration 1044/ 3814 | consumed samples: 534528 | consumed tokens: 1094713344 | elapsed time per iteration (s): 5.95 | learning rate: 4.710E-04 | global batch size: 512 | lm loss: 4.192208E+00 | loss scale: 16384.0 | grad norm: 0.205 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.090 | TFLOPs: 65.02 | +[default7]: iteration 1045/ 3814 | consumed samples: 535040 | consumed tokens: 1095761920 | elapsed time per iteration (s): 5.97 | learning rate: 4.709E-04 | global batch size: 512 | lm loss: 4.184844E+00 | loss scale: 16384.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.774 | TFLOPs: 64.79 | +[default7]: iteration 1046/ 3814 | consumed samples: 535552 | consumed tokens: 1096810496 | elapsed time per iteration (s): 5.91 | learning rate: 4.708E-04 | global batch size: 512 | lm loss: 4.166638E+00 | loss scale: 16384.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.653 | TFLOPs: 65.45 | +[default7]: iteration 1047/ 3814 | consumed samples: 536064 | consumed tokens: 1097859072 | elapsed time per iteration (s): 6.04 | learning rate: 4.706E-04 | global batch size: 512 | lm loss: 4.189878E+00 | loss scale: 16384.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.711 | TFLOPs: 63.98 | +[default7]: iteration 1048/ 3814 | consumed samples: 536576 | consumed tokens: 1098907648 | elapsed time per iteration (s): 6.01 | learning rate: 4.705E-04 | global batch size: 512 | lm loss: 4.207544E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.124 | TFLOPs: 64.29 | +[default7]: iteration 1049/ 3814 | consumed samples: 537088 | consumed tokens: 1099956224 | elapsed time per iteration (s): 5.97 | learning rate: 4.704E-04 | global batch size: 512 | lm loss: 4.187563E+00 | loss scale: 16384.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.745 | TFLOPs: 64.76 | +[default7]: iteration 1050/ 3814 | consumed samples: 537600 | consumed tokens: 1101004800 | elapsed time per iteration (s): 6.00 | learning rate: 4.702E-04 | global batch size: 512 | lm loss: 4.198227E+00 | loss scale: 16384.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 1051/ 3814 | consumed samples: 538112 | consumed tokens: 1102053376 | elapsed time per iteration (s): 5.97 | learning rate: 4.701E-04 | global batch size: 512 | lm loss: 4.171655E+00 | loss scale: 16384.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.726 | TFLOPs: 64.75 | +[default7]: iteration 1052/ 3814 | consumed samples: 538624 | consumed tokens: 1103101952 | elapsed time per iteration (s): 5.67 | learning rate: 4.699E-04 | global batch size: 512 | lm loss: 4.194063E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.277 | TFLOPs: 68.19 | +[default7]: iteration 1053/ 3814 | consumed samples: 539136 | consumed tokens: 1104150528 | elapsed time per iteration (s): 5.99 | learning rate: 4.698E-04 | global batch size: 512 | lm loss: 4.168732E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.472 | TFLOPs: 64.56 | +[default7]: iteration 1054/ 3814 | consumed samples: 539648 | consumed tokens: 1105199104 | elapsed time per iteration (s): 5.96 | learning rate: 4.697E-04 | global batch size: 512 | lm loss: 4.171761E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.963 | TFLOPs: 64.93 | +[default7]: iteration 1055/ 3814 | consumed samples: 540160 | consumed tokens: 1106247680 | elapsed time per iteration (s): 5.99 | learning rate: 4.695E-04 | global batch size: 512 | lm loss: 4.176980E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.469 | TFLOPs: 64.56 | +[default7]: iteration 1056/ 3814 | consumed samples: 540672 | consumed tokens: 1107296256 | elapsed time per iteration (s): 5.99 | learning rate: 4.694E-04 | global batch size: 512 | lm loss: 4.194623E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.426 | TFLOPs: 64.52 | +[default7]: iteration 1057/ 3814 | consumed samples: 541184 | consumed tokens: 1108344832 | elapsed time per iteration (s): 5.95 | learning rate: 4.692E-04 | global batch size: 512 | lm loss: 4.235030E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.011 | TFLOPs: 64.96 | +[default7]: iteration 1058/ 3814 | consumed samples: 541696 | consumed tokens: 1109393408 | elapsed time per iteration (s): 5.92 | learning rate: 4.691E-04 | global batch size: 512 | lm loss: 4.176050E+00 | loss scale: 16384.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.432 | TFLOPs: 65.28 | +[default7]: iteration 1059/ 3814 | consumed samples: 542208 | consumed tokens: 1110441984 | elapsed time per iteration (s): 5.95 | learning rate: 4.690E-04 | global batch size: 512 | lm loss: 4.190965E+00 | loss scale: 16384.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.038 | TFLOPs: 64.99 | +[default7]: iteration 1060/ 3814 | consumed samples: 542720 | consumed tokens: 1111490560 | elapsed time per iteration (s): 6.16 | learning rate: 4.688E-04 | global batch size: 512 | lm loss: 4.173913E+00 | loss scale: 16384.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.070 | TFLOPs: 62.74 | +[default7]: iteration 1061/ 3814 | consumed samples: 543232 | consumed tokens: 1112539136 | elapsed time per iteration (s): 6.20 | learning rate: 4.687E-04 | global batch size: 512 | lm loss: 4.201568E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.643 | TFLOPs: 62.42 | +[default7]: iteration 1062/ 3814 | consumed samples: 543744 | consumed tokens: 1113587712 | elapsed time per iteration (s): 6.01 | learning rate: 4.685E-04 | global batch size: 512 | lm loss: 4.137408E+00 | loss scale: 16384.0 | grad norm: 0.190 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.219 | TFLOPs: 64.37 | +[default7]: iteration 1063/ 3814 | consumed samples: 544256 | consumed tokens: 1114636288 | elapsed time per iteration (s): 5.99 | learning rate: 4.684E-04 | global batch size: 512 | lm loss: 4.159650E+00 | loss scale: 16384.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.525 | TFLOPs: 64.60 | +[default7]: iteration 1064/ 3814 | consumed samples: 544768 | consumed tokens: 1115684864 | elapsed time per iteration (s): 5.98 | learning rate: 4.682E-04 | global batch size: 512 | lm loss: 4.178264E+00 | loss scale: 16384.0 | grad norm: 0.213 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.554 | TFLOPs: 64.62 | +[default7]: iteration 1065/ 3814 | consumed samples: 545280 | consumed tokens: 1116733440 | elapsed time per iteration (s): 5.95 | learning rate: 4.681E-04 | global batch size: 512 | lm loss: 4.194798E+00 | loss scale: 16384.0 | grad norm: 0.246 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.100 | TFLOPs: 65.03 | +[default7]: iteration 1066/ 3814 | consumed samples: 545792 | consumed tokens: 1117782016 | elapsed time per iteration (s): 5.97 | learning rate: 4.680E-04 | global batch size: 512 | lm loss: 4.191484E+00 | loss scale: 16384.0 | grad norm: 0.207 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.799 | TFLOPs: 64.80 | +[default7]: iteration 1067/ 3814 | consumed samples: 546304 | consumed tokens: 1118830592 | elapsed time per iteration (s): 5.97 | learning rate: 4.678E-04 | global batch size: 512 | lm loss: 4.154158E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.748 | TFLOPs: 64.77 | +[default7]: iteration 1068/ 3814 | consumed samples: 546816 | consumed tokens: 1119879168 | elapsed time per iteration (s): 6.13 | learning rate: 4.677E-04 | global batch size: 512 | lm loss: 4.161368E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.531 | TFLOPs: 63.09 | +[default7]: iteration 1069/ 3814 | consumed samples: 547328 | consumed tokens: 1120927744 | elapsed time per iteration (s): 6.17 | learning rate: 4.675E-04 | global batch size: 512 | lm loss: 4.157418E+00 | loss scale: 16384.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.931 | TFLOPs: 62.64 | +[default7]: iteration 1070/ 3814 | consumed samples: 547840 | consumed tokens: 1121976320 | elapsed time per iteration (s): 6.11 | learning rate: 4.674E-04 | global batch size: 512 | lm loss: 4.163680E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.790 | TFLOPs: 63.29 | +[default7]: iteration 1071/ 3814 | consumed samples: 548352 | consumed tokens: 1123024896 | elapsed time per iteration (s): 6.16 | learning rate: 4.673E-04 | global batch size: 512 | lm loss: 4.159247E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.069 | TFLOPs: 62.74 | +[default7]: iteration 1072/ 3814 | consumed samples: 548864 | consumed tokens: 1124073472 | elapsed time per iteration (s): 6.17 | learning rate: 4.671E-04 | global batch size: 512 | lm loss: 4.134517E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.989 | TFLOPs: 62.68 | +[default7]: iteration 1073/ 3814 | consumed samples: 549376 | consumed tokens: 1125122048 | elapsed time per iteration (s): 6.22 | learning rate: 4.670E-04 | global batch size: 512 | lm loss: 4.153548E+00 | loss scale: 16384.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.277 | TFLOPs: 62.14 | +[default7]: iteration 1074/ 3814 | consumed samples: 549888 | consumed tokens: 1126170624 | elapsed time per iteration (s): 6.13 | learning rate: 4.668E-04 | global batch size: 512 | lm loss: 4.136765E+00 | loss scale: 16384.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.589 | TFLOPs: 63.14 | +[default7]: iteration 1075/ 3814 | consumed samples: 550400 | consumed tokens: 1127219200 | elapsed time per iteration (s): 6.20 | learning rate: 4.667E-04 | global batch size: 512 | lm loss: 4.139234E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.545 | TFLOPs: 62.35 | +[default7]: iteration 1076/ 3814 | consumed samples: 550912 | consumed tokens: 1128267776 | elapsed time per iteration (s): 5.93 | learning rate: 4.665E-04 | global batch size: 512 | lm loss: 4.138505E+00 | loss scale: 16384.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.318 | TFLOPs: 65.20 | +[default7]: iteration 1077/ 3814 | consumed samples: 551424 | consumed tokens: 1129316352 | elapsed time per iteration (s): 6.14 | learning rate: 4.664E-04 | global batch size: 512 | lm loss: 4.130649E+00 | loss scale: 16384.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.449 | TFLOPs: 63.03 | +[default7]: iteration 1078/ 3814 | consumed samples: 551936 | consumed tokens: 1130364928 | elapsed time per iteration (s): 6.12 | learning rate: 4.663E-04 | global batch size: 512 | lm loss: 4.158313E+00 | loss scale: 16384.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.613 | TFLOPs: 63.15 | +[default7]: iteration 1079/ 3814 | consumed samples: 552448 | consumed tokens: 1131413504 | elapsed time per iteration (s): 6.15 | learning rate: 4.661E-04 | global batch size: 512 | lm loss: 4.118486E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.235 | TFLOPs: 62.87 | +[default7]: iteration 1080/ 3814 | consumed samples: 552960 | consumed tokens: 1132462080 | elapsed time per iteration (s): 6.16 | learning rate: 4.660E-04 | global batch size: 512 | lm loss: 4.132010E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.181 | TFLOPs: 62.83 | +[default7]: iteration 1081/ 3814 | consumed samples: 553472 | consumed tokens: 1133510656 | elapsed time per iteration (s): 5.96 | learning rate: 4.658E-04 | global batch size: 512 | lm loss: 4.148708E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.967 | TFLOPs: 64.93 | +[default7]: iteration 1082/ 3814 | consumed samples: 553984 | consumed tokens: 1134559232 | elapsed time per iteration (s): 6.26 | learning rate: 4.657E-04 | global batch size: 512 | lm loss: 4.148070E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.793 | TFLOPs: 61.78 | +[default7]: iteration 1083/ 3814 | consumed samples: 554496 | consumed tokens: 1135607808 | elapsed time per iteration (s): 6.22 | learning rate: 4.655E-04 | global batch size: 512 | lm loss: 4.155633E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.364 | TFLOPs: 62.21 | +[default7]: iteration 1084/ 3814 | consumed samples: 555008 | consumed tokens: 1136656384 | elapsed time per iteration (s): 6.05 | learning rate: 4.654E-04 | global batch size: 512 | lm loss: 4.132756E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.575 | TFLOPs: 63.88 | +[default7]: iteration 1085/ 3814 | consumed samples: 555520 | consumed tokens: 1137704960 | elapsed time per iteration (s): 6.09 | learning rate: 4.652E-04 | global batch size: 512 | lm loss: 4.151106E+00 | loss scale: 16384.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.113 | TFLOPs: 63.53 | +[default7]: iteration 1086/ 3814 | consumed samples: 556032 | consumed tokens: 1138753536 | elapsed time per iteration (s): 6.19 | learning rate: 4.651E-04 | global batch size: 512 | lm loss: 4.125364E+00 | loss scale: 16384.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.695 | TFLOPs: 62.46 | +[default7]: iteration 1087/ 3814 | consumed samples: 556544 | consumed tokens: 1139802112 | elapsed time per iteration (s): 6.04 | learning rate: 4.649E-04 | global batch size: 512 | lm loss: 4.115927E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.711 | TFLOPs: 63.98 | +[default7]: iteration 1088/ 3814 | consumed samples: 557056 | consumed tokens: 1140850688 | elapsed time per iteration (s): 6.17 | learning rate: 4.648E-04 | global batch size: 512 | lm loss: 4.119575E+00 | loss scale: 16384.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.957 | TFLOPs: 62.66 | +[default7]: iteration 1089/ 3814 | consumed samples: 557568 | consumed tokens: 1141899264 | elapsed time per iteration (s): 6.12 | learning rate: 4.647E-04 | global batch size: 512 | lm loss: 4.147117E+00 | loss scale: 16384.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.598 | TFLOPs: 63.14 | +[default7]: iteration 1090/ 3814 | consumed samples: 558080 | consumed tokens: 1142947840 | elapsed time per iteration (s): 6.16 | learning rate: 4.645E-04 | global batch size: 512 | lm loss: 4.141945E+00 | loss scale: 16384.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.144 | TFLOPs: 62.80 | +[default7]: iteration 1091/ 3814 | consumed samples: 558592 | consumed tokens: 1143996416 | elapsed time per iteration (s): 6.21 | learning rate: 4.644E-04 | global batch size: 512 | lm loss: 4.113568E+00 | loss scale: 16384.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.500 | TFLOPs: 62.31 | +[default7]: iteration 1092/ 3814 | consumed samples: 559104 | consumed tokens: 1145044992 | elapsed time per iteration (s): 6.15 | learning rate: 4.642E-04 | global batch size: 512 | lm loss: 4.116885E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.239 | TFLOPs: 62.87 | +[default7]: iteration 1093/ 3814 | consumed samples: 559616 | consumed tokens: 1146093568 | elapsed time per iteration (s): 6.26 | learning rate: 4.641E-04 | global batch size: 512 | lm loss: 4.114015E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.749 | TFLOPs: 61.75 | +[default7]: iteration 1094/ 3814 | consumed samples: 560128 | consumed tokens: 1147142144 | elapsed time per iteration (s): 6.06 | learning rate: 4.639E-04 | global batch size: 512 | lm loss: 4.133893E+00 | loss scale: 16384.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.490 | TFLOPs: 63.82 | +[default7]: iteration 1095/ 3814 | consumed samples: 560640 | consumed tokens: 1148190720 | elapsed time per iteration (s): 6.16 | learning rate: 4.638E-04 | global batch size: 512 | lm loss: 4.121629E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.085 | TFLOPs: 62.75 | +[default7]: iteration 1096/ 3814 | consumed samples: 561152 | consumed tokens: 1149239296 | elapsed time per iteration (s): 6.17 | learning rate: 4.636E-04 | global batch size: 512 | lm loss: 4.137635E+00 | loss scale: 16384.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.006 | TFLOPs: 62.70 | +[default7]: iteration 1097/ 3814 | consumed samples: 561664 | consumed tokens: 1150287872 | elapsed time per iteration (s): 6.24 | learning rate: 4.635E-04 | global batch size: 512 | lm loss: 4.142875E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.107 | TFLOPs: 62.02 | +[default7]: iteration 1098/ 3814 | consumed samples: 562176 | consumed tokens: 1151336448 | elapsed time per iteration (s): 6.16 | learning rate: 4.633E-04 | global batch size: 512 | lm loss: 4.129019E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.119 | TFLOPs: 62.78 | +[default7]: iteration 1099/ 3814 | consumed samples: 562688 | consumed tokens: 1152385024 | elapsed time per iteration (s): 6.13 | learning rate: 4.632E-04 | global batch size: 512 | lm loss: 4.103702E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.470 | TFLOPs: 63.05 | +[default7]: iteration 1100/ 3814 | consumed samples: 563200 | consumed tokens: 1153433600 | elapsed time per iteration (s): 5.99 | learning rate: 4.630E-04 | global batch size: 512 | lm loss: 4.108146E+00 | loss scale: 16384.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.541 | TFLOPs: 64.61 | +[default7]: iteration 1101/ 3814 | consumed samples: 563712 | consumed tokens: 1154482176 | elapsed time per iteration (s): 5.98 | learning rate: 4.629E-04 | global batch size: 512 | lm loss: 4.105793E+00 | loss scale: 16384.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.666 | TFLOPs: 64.70 | +[default7]: iteration 1102/ 3814 | consumed samples: 564224 | consumed tokens: 1155530752 | elapsed time per iteration (s): 6.00 | learning rate: 4.627E-04 | global batch size: 512 | lm loss: 4.122309E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.312 | TFLOPs: 64.44 | +[default7]: iteration 1103/ 3814 | consumed samples: 564736 | consumed tokens: 1156579328 | elapsed time per iteration (s): 6.01 | learning rate: 4.626E-04 | global batch size: 512 | lm loss: 4.108337E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.242 | TFLOPs: 64.38 | +[default7]: iteration 1104/ 3814 | consumed samples: 565248 | consumed tokens: 1157627904 | elapsed time per iteration (s): 6.05 | learning rate: 4.625E-04 | global batch size: 512 | lm loss: 4.109260E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.649 | TFLOPs: 63.94 | +[default7]: iteration 1105/ 3814 | consumed samples: 565760 | consumed tokens: 1158676480 | elapsed time per iteration (s): 6.00 | learning rate: 4.623E-04 | global batch size: 512 | lm loss: 4.128586E+00 | loss scale: 16384.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.396 | TFLOPs: 64.50 | +[default7]: iteration 1106/ 3814 | consumed samples: 566272 | consumed tokens: 1159725056 | elapsed time per iteration (s): 5.96 | learning rate: 4.622E-04 | global batch size: 512 | lm loss: 4.102433E+00 | loss scale: 16384.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.977 | TFLOPs: 64.94 | +[default7]: iteration 1107/ 3814 | consumed samples: 566784 | consumed tokens: 1160773632 | elapsed time per iteration (s): 6.00 | learning rate: 4.620E-04 | global batch size: 512 | lm loss: 4.115132E+00 | loss scale: 16384.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.318 | TFLOPs: 64.44 | +[default7]: iteration 1108/ 3814 | consumed samples: 567296 | consumed tokens: 1161822208 | elapsed time per iteration (s): 6.00 | learning rate: 4.619E-04 | global batch size: 512 | lm loss: 4.106122E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.310 | TFLOPs: 64.44 | +[default7]: iteration 1109/ 3814 | consumed samples: 567808 | consumed tokens: 1162870784 | elapsed time per iteration (s): 5.97 | learning rate: 4.617E-04 | global batch size: 512 | lm loss: 4.089385E+00 | loss scale: 16384.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.703 | TFLOPs: 64.73 | +[default7]: iteration 1110/ 3814 | consumed samples: 568320 | consumed tokens: 1163919360 | elapsed time per iteration (s): 5.96 | learning rate: 4.616E-04 | global batch size: 512 | lm loss: 4.116207E+00 | loss scale: 16384.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.896 | TFLOPs: 64.88 | +[default7]: iteration 1111/ 3814 | consumed samples: 568832 | consumed tokens: 1164967936 | elapsed time per iteration (s): 5.95 | learning rate: 4.614E-04 | global batch size: 512 | lm loss: 4.097433E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.058 | TFLOPs: 65.00 | +[default7]: iteration 1112/ 3814 | consumed samples: 569344 | consumed tokens: 1166016512 | elapsed time per iteration (s): 6.15 | learning rate: 4.613E-04 | global batch size: 512 | lm loss: 4.099225E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.290 | TFLOPs: 62.91 | +[default7]: iteration 1113/ 3814 | consumed samples: 569856 | consumed tokens: 1167065088 | elapsed time per iteration (s): 5.98 | learning rate: 4.611E-04 | global batch size: 512 | lm loss: 4.081700E+00 | loss scale: 16384.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.689 | TFLOPs: 64.72 | +[default7]: iteration 1114/ 3814 | consumed samples: 570368 | consumed tokens: 1168113664 | elapsed time per iteration (s): 6.15 | learning rate: 4.610E-04 | global batch size: 512 | lm loss: 4.087960E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.234 | TFLOPs: 62.87 | +[default7]: iteration 1115/ 3814 | consumed samples: 570880 | consumed tokens: 1169162240 | elapsed time per iteration (s): 6.02 | learning rate: 4.608E-04 | global batch size: 512 | lm loss: 4.082049E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.073 | TFLOPs: 64.26 | +[default7]: iteration 1116/ 3814 | consumed samples: 571392 | consumed tokens: 1170210816 | elapsed time per iteration (s): 5.93 | learning rate: 4.607E-04 | global batch size: 512 | lm loss: 4.106722E+00 | loss scale: 16384.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.410 | TFLOPs: 65.27 | +[default7]: iteration 1117/ 3814 | consumed samples: 571904 | consumed tokens: 1171259392 | elapsed time per iteration (s): 5.98 | learning rate: 4.605E-04 | global batch size: 512 | lm loss: 4.115102E+00 | loss scale: 16384.0 | grad norm: 0.203 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.602 | TFLOPs: 64.66 | +[default7]: iteration 1118/ 3814 | consumed samples: 572416 | consumed tokens: 1172307968 | elapsed time per iteration (s): 5.82 | learning rate: 4.604E-04 | global batch size: 512 | lm loss: 4.111266E+00 | loss scale: 16384.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.019 | TFLOPs: 66.48 | +[default7]: iteration 1119/ 3814 | consumed samples: 572928 | consumed tokens: 1173356544 | elapsed time per iteration (s): 5.94 | learning rate: 4.602E-04 | global batch size: 512 | lm loss: 4.118487E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.152 | TFLOPs: 65.07 | +[default7]: iteration 1120/ 3814 | consumed samples: 573440 | consumed tokens: 1174405120 | elapsed time per iteration (s): 5.97 | learning rate: 4.601E-04 | global batch size: 512 | lm loss: 4.102229E+00 | loss scale: 16384.0 | grad norm: 0.235 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.764 | TFLOPs: 64.78 | +[default7]: iteration 1121/ 3814 | consumed samples: 573952 | consumed tokens: 1175453696 | elapsed time per iteration (s): 6.03 | learning rate: 4.599E-04 | global batch size: 512 | lm loss: 4.102570E+00 | loss scale: 16384.0 | grad norm: 0.247 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.879 | TFLOPs: 64.11 | +[default7]: iteration 1122/ 3814 | consumed samples: 574464 | consumed tokens: 1176502272 | elapsed time per iteration (s): 5.88 | learning rate: 4.598E-04 | global batch size: 512 | lm loss: 4.105171E+00 | loss scale: 16384.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.047 | TFLOPs: 65.75 | +[default7]: iteration 1123/ 3814 | consumed samples: 574976 | consumed tokens: 1177550848 | elapsed time per iteration (s): 5.98 | learning rate: 4.596E-04 | global batch size: 512 | lm loss: 4.083596E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.625 | TFLOPs: 64.67 | +[default7]: iteration 1124/ 3814 | consumed samples: 575488 | consumed tokens: 1178599424 | elapsed time per iteration (s): 5.97 | learning rate: 4.595E-04 | global batch size: 512 | lm loss: 4.068968E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.804 | TFLOPs: 64.81 | +[default7]: iteration 1125/ 3814 | consumed samples: 576000 | consumed tokens: 1179648000 | elapsed time per iteration (s): 5.96 | learning rate: 4.593E-04 | global batch size: 512 | lm loss: 4.086108E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.965 | TFLOPs: 64.93 | +[default7]: iteration 1126/ 3814 | consumed samples: 576512 | consumed tokens: 1180696576 | elapsed time per iteration (s): 5.95 | learning rate: 4.592E-04 | global batch size: 512 | lm loss: 4.102935E+00 | loss scale: 16384.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.049 | TFLOPs: 64.99 | +[default7]: iteration 1127/ 3814 | consumed samples: 577024 | consumed tokens: 1181745152 | elapsed time per iteration (s): 5.97 | learning rate: 4.590E-04 | global batch size: 512 | lm loss: 4.075639E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.793 | TFLOPs: 64.80 | +[default7]: iteration 1128/ 3814 | consumed samples: 577536 | consumed tokens: 1182793728 | elapsed time per iteration (s): 5.94 | learning rate: 4.588E-04 | global batch size: 512 | lm loss: 4.076054E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.188 | TFLOPs: 65.10 | +[default7]: iteration 1129/ 3814 | consumed samples: 578048 | consumed tokens: 1183842304 | elapsed time per iteration (s): 5.89 | learning rate: 4.587E-04 | global batch size: 512 | lm loss: 4.100965E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.895 | TFLOPs: 65.63 | +[default7]: iteration 1130/ 3814 | consumed samples: 578560 | consumed tokens: 1184890880 | elapsed time per iteration (s): 5.95 | learning rate: 4.585E-04 | global batch size: 512 | lm loss: 4.094383E+00 | loss scale: 16384.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.979 | TFLOPs: 64.94 | +[default7]: iteration 1131/ 3814 | consumed samples: 579072 | consumed tokens: 1185939456 | elapsed time per iteration (s): 6.23 | learning rate: 4.584E-04 | global batch size: 512 | lm loss: 4.089074E+00 | loss scale: 16384.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.246 | TFLOPs: 62.12 | +[default7]: iteration 1132/ 3814 | consumed samples: 579584 | consumed tokens: 1186988032 | elapsed time per iteration (s): 6.07 | learning rate: 4.582E-04 | global batch size: 512 | lm loss: 4.085166E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.366 | TFLOPs: 63.72 | +[default7]: iteration 1133/ 3814 | consumed samples: 580096 | consumed tokens: 1188036608 | elapsed time per iteration (s): 6.03 | learning rate: 4.581E-04 | global batch size: 512 | lm loss: 4.096125E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.962 | TFLOPs: 64.17 | +[default7]: iteration 1134/ 3814 | consumed samples: 580608 | consumed tokens: 1189085184 | elapsed time per iteration (s): 5.95 | learning rate: 4.579E-04 | global batch size: 512 | lm loss: 4.078010E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.979 | TFLOPs: 64.94 | +[default7]: iteration 1135/ 3814 | consumed samples: 581120 | consumed tokens: 1190133760 | elapsed time per iteration (s): 6.02 | learning rate: 4.578E-04 | global batch size: 512 | lm loss: 4.035584E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.099 | TFLOPs: 64.28 | +[default7]: iteration 1136/ 3814 | consumed samples: 581632 | consumed tokens: 1191182336 | elapsed time per iteration (s): 5.98 | learning rate: 4.576E-04 | global batch size: 512 | lm loss: 4.024834E+00 | loss scale: 16384.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.675 | TFLOPs: 64.71 | +[default7]: iteration 1137/ 3814 | consumed samples: 582144 | consumed tokens: 1192230912 | elapsed time per iteration (s): 6.24 | learning rate: 4.575E-04 | global batch size: 512 | lm loss: 4.049076E+00 | loss scale: 16384.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.116 | TFLOPs: 62.02 | +[default7]: iteration 1138/ 3814 | consumed samples: 582656 | consumed tokens: 1193279488 | elapsed time per iteration (s): 5.95 | learning rate: 4.573E-04 | global batch size: 512 | lm loss: 4.064092E+00 | loss scale: 16384.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.097 | TFLOPs: 65.03 | +[default7]: iteration 1139/ 3814 | consumed samples: 583168 | consumed tokens: 1194328064 | elapsed time per iteration (s): 6.04 | learning rate: 4.572E-04 | global batch size: 512 | lm loss: 4.053473E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.747 | TFLOPs: 64.01 | +[default7]: iteration 1140/ 3814 | consumed samples: 583680 | consumed tokens: 1195376640 | elapsed time per iteration (s): 6.02 | learning rate: 4.570E-04 | global batch size: 512 | lm loss: 4.043210E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.120 | TFLOPs: 64.29 | +[default7]: iteration 1141/ 3814 | consumed samples: 584192 | consumed tokens: 1196425216 | elapsed time per iteration (s): 5.99 | learning rate: 4.569E-04 | global batch size: 512 | lm loss: 4.065107E+00 | loss scale: 16384.0 | grad norm: 0.191 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.415 | TFLOPs: 64.51 | +[default7]: iteration 1142/ 3814 | consumed samples: 584704 | consumed tokens: 1197473792 | elapsed time per iteration (s): 6.21 | learning rate: 4.567E-04 | global batch size: 512 | lm loss: 4.050918E+00 | loss scale: 16384.0 | grad norm: 0.210 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.492 | TFLOPs: 62.31 | +[default7]: iteration 1143/ 3814 | consumed samples: 585216 | consumed tokens: 1198522368 | elapsed time per iteration (s): 6.21 | learning rate: 4.565E-04 | global batch size: 512 | lm loss: 4.058074E+00 | loss scale: 16384.0 | grad norm: 0.198 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.447 | TFLOPs: 62.27 | +[default7]: iteration 1144/ 3814 | consumed samples: 585728 | consumed tokens: 1199570944 | elapsed time per iteration (s): 6.16 | learning rate: 4.564E-04 | global batch size: 512 | lm loss: 4.040868E+00 | loss scale: 16384.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.088 | TFLOPs: 62.76 | +[default7]: iteration 1145/ 3814 | consumed samples: 586240 | consumed tokens: 1200619520 | elapsed time per iteration (s): 6.09 | learning rate: 4.562E-04 | global batch size: 512 | lm loss: 4.049039E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.056 | TFLOPs: 63.49 | +[default7]: iteration 1146/ 3814 | consumed samples: 586752 | consumed tokens: 1201668096 | elapsed time per iteration (s): 6.12 | learning rate: 4.561E-04 | global batch size: 512 | lm loss: 4.089999E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.659 | TFLOPs: 63.19 | +[default7]: iteration 1147/ 3814 | consumed samples: 587264 | consumed tokens: 1202716672 | elapsed time per iteration (s): 6.18 | learning rate: 4.559E-04 | global batch size: 512 | lm loss: 4.030167E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.886 | TFLOPs: 62.60 | +[default7]: iteration 1148/ 3814 | consumed samples: 587776 | consumed tokens: 1203765248 | elapsed time per iteration (s): 6.13 | learning rate: 4.558E-04 | global batch size: 512 | lm loss: 4.040244E+00 | loss scale: 16384.0 | grad norm: 0.233 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.592 | TFLOPs: 63.14 | +[default7]: iteration 1149/ 3814 | consumed samples: 588288 | consumed tokens: 1204813824 | elapsed time per iteration (s): 6.31 | learning rate: 4.556E-04 | global batch size: 512 | lm loss: 4.070868E+00 | loss scale: 16384.0 | grad norm: 0.258 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.182 | TFLOPs: 61.32 | +[default7]: iteration 1150/ 3814 | consumed samples: 588800 | consumed tokens: 1205862400 | elapsed time per iteration (s): 6.15 | learning rate: 4.555E-04 | global batch size: 512 | lm loss: 4.045972E+00 | loss scale: 16384.0 | grad norm: 0.184 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.248 | TFLOPs: 62.88 | +[default7]: iteration 1151/ 3814 | consumed samples: 589312 | consumed tokens: 1206910976 | elapsed time per iteration (s): 6.14 | learning rate: 4.553E-04 | global batch size: 512 | lm loss: 4.048159E+00 | loss scale: 16384.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.360 | TFLOPs: 62.96 | +[default7]: iteration 1152/ 3814 | consumed samples: 589824 | consumed tokens: 1207959552 | elapsed time per iteration (s): 6.18 | learning rate: 4.551E-04 | global batch size: 512 | lm loss: 4.089331E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.899 | TFLOPs: 62.61 | +[default7]: iteration 1153/ 3814 | consumed samples: 590336 | consumed tokens: 1209008128 | elapsed time per iteration (s): 6.14 | learning rate: 4.550E-04 | global batch size: 512 | lm loss: 4.036184E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.348 | TFLOPs: 62.95 | +[default7]: iteration 1154/ 3814 | consumed samples: 590848 | consumed tokens: 1210056704 | elapsed time per iteration (s): 6.21 | learning rate: 4.548E-04 | global batch size: 512 | lm loss: 4.064967E+00 | loss scale: 16384.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.512 | TFLOPs: 62.32 | +[default7]: iteration 1155/ 3814 | consumed samples: 591360 | consumed tokens: 1211105280 | elapsed time per iteration (s): 6.02 | learning rate: 4.547E-04 | global batch size: 512 | lm loss: 4.046819E+00 | loss scale: 16384.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.072 | TFLOPs: 64.26 | +[default7]: iteration 1156/ 3814 | consumed samples: 591872 | consumed tokens: 1212153856 | elapsed time per iteration (s): 6.09 | learning rate: 4.545E-04 | global batch size: 512 | lm loss: 4.051829E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.044 | TFLOPs: 63.48 | +[default7]: iteration 1157/ 3814 | consumed samples: 592384 | consumed tokens: 1213202432 | elapsed time per iteration (s): 6.15 | learning rate: 4.544E-04 | global batch size: 512 | lm loss: 4.090364E+00 | loss scale: 16384.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.312 | TFLOPs: 62.93 | +[default7]: iteration 1158/ 3814 | consumed samples: 592896 | consumed tokens: 1214251008 | elapsed time per iteration (s): 6.20 | learning rate: 4.542E-04 | global batch size: 512 | lm loss: 4.023329E+00 | loss scale: 16384.0 | grad norm: 0.172 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.590 | TFLOPs: 62.38 | +[default7]: iteration 1159/ 3814 | consumed samples: 593408 | consumed tokens: 1215299584 | elapsed time per iteration (s): 6.12 | learning rate: 4.540E-04 | global batch size: 512 | lm loss: 4.047281E+00 | loss scale: 16384.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.606 | TFLOPs: 63.15 | +[default7]: iteration 1160/ 3814 | consumed samples: 593920 | consumed tokens: 1216348160 | elapsed time per iteration (s): 6.14 | learning rate: 4.539E-04 | global batch size: 512 | lm loss: 4.050191E+00 | loss scale: 16384.0 | grad norm: 0.196 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.441 | TFLOPs: 63.02 | +[default7]: iteration 1161/ 3814 | consumed samples: 594432 | consumed tokens: 1217396736 | elapsed time per iteration (s): 6.09 | learning rate: 4.537E-04 | global batch size: 512 | lm loss: 4.057701E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.091 | TFLOPs: 63.51 | +[default7]: iteration 1162/ 3814 | consumed samples: 594944 | consumed tokens: 1218445312 | elapsed time per iteration (s): 5.99 | learning rate: 4.536E-04 | global batch size: 512 | lm loss: 4.071074E+00 | loss scale: 16384.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.452 | TFLOPs: 64.54 | +[default7]: iteration 1163/ 3814 | consumed samples: 595456 | consumed tokens: 1219493888 | elapsed time per iteration (s): 5.99 | learning rate: 4.534E-04 | global batch size: 512 | lm loss: 4.072562E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.538 | TFLOPs: 64.61 | +[default7]: iteration 1164/ 3814 | consumed samples: 595968 | consumed tokens: 1220542464 | elapsed time per iteration (s): 5.95 | learning rate: 4.533E-04 | global batch size: 512 | lm loss: 4.036897E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.096 | TFLOPs: 65.03 | +[default7]: iteration 1165/ 3814 | consumed samples: 596480 | consumed tokens: 1221591040 | elapsed time per iteration (s): 5.94 | learning rate: 4.531E-04 | global batch size: 512 | lm loss: 4.026186E+00 | loss scale: 16384.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.169 | TFLOPs: 65.08 | +[default7]: iteration 1166/ 3814 | consumed samples: 596992 | consumed tokens: 1222639616 | elapsed time per iteration (s): 5.99 | learning rate: 4.529E-04 | global batch size: 512 | lm loss: 3.990221E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.422 | TFLOPs: 64.52 | +[default7]: iteration 1167/ 3814 | consumed samples: 597504 | consumed tokens: 1223688192 | elapsed time per iteration (s): 5.99 | learning rate: 4.528E-04 | global batch size: 512 | lm loss: 4.062924E+00 | loss scale: 16384.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.531 | TFLOPs: 64.60 | +[default7]: iteration 1168/ 3814 | consumed samples: 598016 | consumed tokens: 1224736768 | elapsed time per iteration (s): 6.20 | learning rate: 4.526E-04 | global batch size: 512 | lm loss: 4.039218E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.542 | TFLOPs: 62.34 | +[default7]: iteration 1169/ 3814 | consumed samples: 598528 | consumed tokens: 1225785344 | elapsed time per iteration (s): 5.98 | learning rate: 4.525E-04 | global batch size: 512 | lm loss: 4.030570E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.638 | TFLOPs: 64.68 | +[default7]: iteration 1170/ 3814 | consumed samples: 599040 | consumed tokens: 1226833920 | elapsed time per iteration (s): 5.99 | learning rate: 4.523E-04 | global batch size: 512 | lm loss: 4.035085E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.535 | TFLOPs: 64.61 | +[default7]: iteration 1171/ 3814 | consumed samples: 599552 | consumed tokens: 1227882496 | elapsed time per iteration (s): 6.05 | learning rate: 4.522E-04 | global batch size: 512 | lm loss: 4.027824E+00 | loss scale: 16384.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.587 | TFLOPs: 63.89 | +[default7]: iteration 1172/ 3814 | consumed samples: 600064 | consumed tokens: 1228931072 | elapsed time per iteration (s): 5.96 | learning rate: 4.520E-04 | global batch size: 512 | lm loss: 4.028114E+00 | loss scale: 16384.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.896 | TFLOPs: 64.88 | +[default7]: iteration 1173/ 3814 | consumed samples: 600576 | consumed tokens: 1229979648 | elapsed time per iteration (s): 6.17 | learning rate: 4.518E-04 | global batch size: 512 | lm loss: 4.045702E+00 | loss scale: 16384.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.933 | TFLOPs: 62.64 | +[default7]: iteration 1174/ 3814 | consumed samples: 601088 | consumed tokens: 1231028224 | elapsed time per iteration (s): 6.09 | learning rate: 4.517E-04 | global batch size: 512 | lm loss: 4.025680E+00 | loss scale: 16384.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.083 | TFLOPs: 63.51 | +[default7]: iteration 1175/ 3814 | consumed samples: 601600 | consumed tokens: 1232076800 | elapsed time per iteration (s): 5.98 | learning rate: 4.515E-04 | global batch size: 512 | lm loss: 3.982999E+00 | loss scale: 16384.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.568 | TFLOPs: 64.63 | +[default7]: iteration 1176/ 3814 | consumed samples: 602112 | consumed tokens: 1233125376 | elapsed time per iteration (s): 5.99 | learning rate: 4.514E-04 | global batch size: 512 | lm loss: 3.978131E+00 | loss scale: 16384.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.438 | TFLOPs: 64.53 | +[default7]: iteration 1177/ 3814 | consumed samples: 602624 | consumed tokens: 1234173952 | elapsed time per iteration (s): 5.99 | learning rate: 4.512E-04 | global batch size: 512 | lm loss: 4.019637E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.463 | TFLOPs: 64.55 | +[default7]: iteration 1178/ 3814 | consumed samples: 603136 | consumed tokens: 1235222528 | elapsed time per iteration (s): 6.05 | learning rate: 4.510E-04 | global batch size: 512 | lm loss: 4.006708E+00 | loss scale: 16384.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.669 | TFLOPs: 63.95 | +[default7]: iteration 1179/ 3814 | consumed samples: 603648 | consumed tokens: 1236271104 | elapsed time per iteration (s): 6.01 | learning rate: 4.509E-04 | global batch size: 512 | lm loss: 4.034496E+00 | loss scale: 16384.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.138 | TFLOPs: 64.31 | +[default7]: iteration 1180/ 3814 | consumed samples: 604160 | consumed tokens: 1237319680 | elapsed time per iteration (s): 6.04 | learning rate: 4.507E-04 | global batch size: 512 | lm loss: 4.022597E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.814 | TFLOPs: 64.06 | +[default7]: iteration 1181/ 3814 | consumed samples: 604672 | consumed tokens: 1238368256 | elapsed time per iteration (s): 6.03 | learning rate: 4.506E-04 | global batch size: 512 | lm loss: 4.006289E+00 | loss scale: 16384.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.882 | TFLOPs: 64.11 | +[default7]: iteration 1182/ 3814 | consumed samples: 605184 | consumed tokens: 1239416832 | elapsed time per iteration (s): 6.01 | learning rate: 4.504E-04 | global batch size: 512 | lm loss: 4.040627E+00 | loss scale: 16384.0 | grad norm: 0.200 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.227 | TFLOPs: 64.37 | +[default7]: iteration 1183/ 3814 | consumed samples: 605696 | consumed tokens: 1240465408 | elapsed time per iteration (s): 6.00 | learning rate: 4.502E-04 | global batch size: 512 | lm loss: 4.003127E+00 | loss scale: 16384.0 | grad norm: 0.173 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.317 | TFLOPs: 64.44 | +[default7]: iteration 1184/ 3814 | consumed samples: 606208 | consumed tokens: 1241513984 | elapsed time per iteration (s): 6.23 | learning rate: 4.501E-04 | global batch size: 512 | lm loss: 4.035794E+00 | loss scale: 16384.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.123 | TFLOPs: 62.03 | +[default7]: iteration 1185/ 3814 | consumed samples: 606720 | consumed tokens: 1242562560 | elapsed time per iteration (s): 6.02 | learning rate: 4.499E-04 | global batch size: 512 | lm loss: 3.996743E+00 | loss scale: 16384.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.029 | TFLOPs: 64.22 | +[default7]: iteration 1186/ 3814 | consumed samples: 607232 | consumed tokens: 1243611136 | elapsed time per iteration (s): 5.97 | learning rate: 4.497E-04 | global batch size: 512 | lm loss: 4.004225E+00 | loss scale: 16384.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.824 | TFLOPs: 64.82 | +[default7]: iteration 1187/ 3814 | consumed samples: 607744 | consumed tokens: 1244659712 | elapsed time per iteration (s): 6.04 | learning rate: 4.496E-04 | global batch size: 512 | lm loss: 4.021463E+00 | loss scale: 16384.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.749 | TFLOPs: 64.01 | +[default7]: iteration 1188/ 3814 | consumed samples: 608256 | consumed tokens: 1245708288 | elapsed time per iteration (s): 5.93 | learning rate: 4.494E-04 | global batch size: 512 | lm loss: 4.001782E+00 | loss scale: 16384.0 | grad norm: 0.175 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.387 | TFLOPs: 65.25 | +[default7]: iteration 1189/ 3814 | consumed samples: 608768 | consumed tokens: 1246756864 | elapsed time per iteration (s): 6.00 | learning rate: 4.493E-04 | global batch size: 512 | lm loss: 4.037677E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.346 | TFLOPs: 64.46 | +[default7]: iteration 1190/ 3814 | consumed samples: 609280 | consumed tokens: 1247805440 | elapsed time per iteration (s): 5.81 | learning rate: 4.491E-04 | global batch size: 512 | lm loss: 4.006169E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.142 | TFLOPs: 66.57 | +[default7]: iteration 1191/ 3814 | consumed samples: 609792 | consumed tokens: 1248854016 | elapsed time per iteration (s): 6.03 | learning rate: 4.489E-04 | global batch size: 512 | lm loss: 4.025643E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.884 | TFLOPs: 64.11 | +[default7]: iteration 1192/ 3814 | consumed samples: 610304 | consumed tokens: 1249902592 | elapsed time per iteration (s): 5.65 | learning rate: 4.488E-04 | global batch size: 512 | lm loss: 3.993765E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.567 | TFLOPs: 68.41 | +[default7]: iteration 1193/ 3814 | consumed samples: 610816 | consumed tokens: 1250951168 | elapsed time per iteration (s): 6.14 | learning rate: 4.486E-04 | global batch size: 512 | lm loss: 4.016524E+00 | loss scale: 16384.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.431 | TFLOPs: 63.02 | +[default7]: iteration 1194/ 3814 | consumed samples: 611328 | consumed tokens: 1251999744 | elapsed time per iteration (s): 6.18 | learning rate: 4.484E-04 | global batch size: 512 | lm loss: 3.992683E+00 | loss scale: 16384.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.833 | TFLOPs: 62.56 | +[default7]: iteration 1195/ 3814 | consumed samples: 611840 | consumed tokens: 1253048320 | elapsed time per iteration (s): 6.14 | learning rate: 4.483E-04 | global batch size: 512 | lm loss: 3.987556E+00 | loss scale: 16384.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.376 | TFLOPs: 62.97 | +[default7]: iteration 1196/ 3814 | consumed samples: 612352 | consumed tokens: 1254096896 | elapsed time per iteration (s): 6.09 | learning rate: 4.481E-04 | global batch size: 512 | lm loss: 3.988789E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.005 | TFLOPs: 63.45 | +[default7]: iteration 1197/ 3814 | consumed samples: 612864 | consumed tokens: 1255145472 | elapsed time per iteration (s): 6.03 | learning rate: 4.480E-04 | global batch size: 512 | lm loss: 3.978522E+00 | loss scale: 16384.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.898 | TFLOPs: 64.12 | +[default7]: iteration 1198/ 3814 | consumed samples: 613376 | consumed tokens: 1256194048 | elapsed time per iteration (s): 6.20 | learning rate: 4.478E-04 | global batch size: 512 | lm loss: 4.014495E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.554 | TFLOPs: 62.35 | +[default7]: iteration 1199/ 3814 | consumed samples: 613888 | consumed tokens: 1257242624 | elapsed time per iteration (s): 6.03 | learning rate: 4.476E-04 | global batch size: 512 | lm loss: 3.973612E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.948 | TFLOPs: 64.16 | +[default7]: iteration 1200/ 3814 | consumed samples: 614400 | consumed tokens: 1258291200 | elapsed time per iteration (s): 6.13 | learning rate: 4.475E-04 | global batch size: 512 | lm loss: 3.985838E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.531 | TFLOPs: 63.09 | +[default7]: iteration 1201/ 3814 | consumed samples: 614912 | consumed tokens: 1259339776 | elapsed time per iteration (s): 6.23 | learning rate: 4.473E-04 | global batch size: 512 | lm loss: 3.973179E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.212 | TFLOPs: 62.10 | +[default7]: iteration 1202/ 3814 | consumed samples: 615424 | consumed tokens: 1260388352 | elapsed time per iteration (s): 6.20 | learning rate: 4.471E-04 | global batch size: 512 | lm loss: 4.016155E+00 | loss scale: 16384.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.578 | TFLOPs: 62.37 | +[default7]: iteration 1203/ 3814 | consumed samples: 615936 | consumed tokens: 1261436928 | elapsed time per iteration (s): 6.16 | learning rate: 4.470E-04 | global batch size: 512 | lm loss: 4.005264E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.135 | TFLOPs: 62.79 | +[default7]: iteration 1204/ 3814 | consumed samples: 616448 | consumed tokens: 1262485504 | elapsed time per iteration (s): 6.21 | learning rate: 4.468E-04 | global batch size: 512 | lm loss: 3.997751E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.425 | TFLOPs: 62.26 | +[default7]: iteration 1205/ 3814 | consumed samples: 616960 | consumed tokens: 1263534080 | elapsed time per iteration (s): 6.02 | learning rate: 4.466E-04 | global batch size: 512 | lm loss: 3.957441E+00 | loss scale: 16384.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.061 | TFLOPs: 64.25 | +[default7]: iteration 1206/ 3814 | consumed samples: 617472 | consumed tokens: 1264582656 | elapsed time per iteration (s): 6.16 | learning rate: 4.465E-04 | global batch size: 512 | lm loss: 3.993806E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.052 | TFLOPs: 62.73 | +[default7]: iteration 1207/ 3814 | consumed samples: 617984 | consumed tokens: 1265631232 | elapsed time per iteration (s): 6.05 | learning rate: 4.463E-04 | global batch size: 512 | lm loss: 3.973974E+00 | loss scale: 16384.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.634 | TFLOPs: 63.92 | +[default7]: iteration 1208/ 3814 | consumed samples: 618496 | consumed tokens: 1266679808 | elapsed time per iteration (s): 6.31 | learning rate: 4.462E-04 | global batch size: 512 | lm loss: 3.954974E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.177 | TFLOPs: 61.31 | +[default7]: iteration 1209/ 3814 | consumed samples: 619008 | consumed tokens: 1267728384 | elapsed time per iteration (s): 6.05 | learning rate: 4.460E-04 | global batch size: 512 | lm loss: 3.982957E+00 | loss scale: 16384.0 | grad norm: 0.195 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.611 | TFLOPs: 63.91 | +[default7]: iteration 1210/ 3814 | consumed samples: 619520 | consumed tokens: 1268776960 | elapsed time per iteration (s): 6.14 | learning rate: 4.458E-04 | global batch size: 512 | lm loss: 3.986722E+00 | loss scale: 16384.0 | grad norm: 0.241 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.408 | TFLOPs: 63.00 | +[default7]: iteration 1211/ 3814 | consumed samples: 620032 | consumed tokens: 1269825536 | elapsed time per iteration (s): 6.20 | learning rate: 4.457E-04 | global batch size: 512 | lm loss: 3.974978E+00 | loss scale: 16384.0 | grad norm: 0.222 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.635 | TFLOPs: 62.42 | +[default7]: iteration 1212/ 3814 | consumed samples: 620544 | consumed tokens: 1270874112 | elapsed time per iteration (s): 6.16 | learning rate: 4.455E-04 | global batch size: 512 | lm loss: 3.966195E+00 | loss scale: 16384.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.073 | TFLOPs: 62.75 | +[default7]: iteration 1213/ 3814 | consumed samples: 621056 | consumed tokens: 1271922688 | elapsed time per iteration (s): 6.16 | learning rate: 4.453E-04 | global batch size: 512 | lm loss: 3.984243E+00 | loss scale: 16384.0 | grad norm: 0.181 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.050 | TFLOPs: 62.73 | +[default7]: iteration 1214/ 3814 | consumed samples: 621568 | consumed tokens: 1272971264 | elapsed time per iteration (s): 6.22 | learning rate: 4.452E-04 | global batch size: 512 | lm loss: 3.970990E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.309 | TFLOPs: 62.17 | +[default7]: iteration 1215/ 3814 | consumed samples: 622080 | consumed tokens: 1274019840 | elapsed time per iteration (s): 6.20 | learning rate: 4.450E-04 | global batch size: 512 | lm loss: 3.983343E+00 | loss scale: 16384.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.597 | TFLOPs: 62.39 | +[default7]: iteration 1216/ 3814 | consumed samples: 622592 | consumed tokens: 1275068416 | elapsed time per iteration (s): 6.06 | learning rate: 4.448E-04 | global batch size: 512 | lm loss: 3.995252E+00 | loss scale: 16384.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.454 | TFLOPs: 63.79 | +[default7]: iteration 1217/ 3814 | consumed samples: 623104 | consumed tokens: 1276116992 | elapsed time per iteration (s): 6.15 | learning rate: 4.447E-04 | global batch size: 512 | lm loss: 3.963369E+00 | loss scale: 16384.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.203 | TFLOPs: 62.84 | +[default7]: iteration 1218/ 3814 | consumed samples: 623616 | consumed tokens: 1277165568 | elapsed time per iteration (s): 6.24 | learning rate: 4.445E-04 | global batch size: 512 | lm loss: 3.993535E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.054 | TFLOPs: 61.98 | +[default7]: iteration 1219/ 3814 | consumed samples: 624128 | consumed tokens: 1278214144 | elapsed time per iteration (s): 6.07 | learning rate: 4.443E-04 | global batch size: 512 | lm loss: 3.965073E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.388 | TFLOPs: 63.74 | +[default7]: iteration 1220/ 3814 | consumed samples: 624640 | consumed tokens: 1279262720 | elapsed time per iteration (s): 6.15 | learning rate: 4.442E-04 | global batch size: 512 | lm loss: 3.976801E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.243 | TFLOPs: 62.87 | +[default7]: iteration 1221/ 3814 | consumed samples: 625152 | consumed tokens: 1280311296 | elapsed time per iteration (s): 6.18 | learning rate: 4.440E-04 | global batch size: 512 | lm loss: 3.996636E+00 | loss scale: 16384.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.781 | TFLOPs: 62.53 | +[default7]: iteration 1222/ 3814 | consumed samples: 625664 | consumed tokens: 1281359872 | elapsed time per iteration (s): 6.21 | learning rate: 4.438E-04 | global batch size: 512 | lm loss: 3.963417E+00 | loss scale: 16384.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.388 | TFLOPs: 62.23 | +[default7]: iteration 1223/ 3814 | consumed samples: 626176 | consumed tokens: 1282408448 | elapsed time per iteration (s): 6.17 | learning rate: 4.437E-04 | global batch size: 512 | lm loss: 3.960236E+00 | loss scale: 16384.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.981 | TFLOPs: 62.68 | +[default7]: iteration 1224/ 3814 | consumed samples: 626688 | consumed tokens: 1283457024 | elapsed time per iteration (s): 5.96 | learning rate: 4.435E-04 | global batch size: 512 | lm loss: 3.975839E+00 | loss scale: 16384.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.890 | TFLOPs: 64.87 | +[default7]: iteration 1225/ 3814 | consumed samples: 627200 | consumed tokens: 1284505600 | elapsed time per iteration (s): 6.08 | learning rate: 4.433E-04 | global batch size: 512 | lm loss: 3.949908E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.185 | TFLOPs: 63.59 | +[default7]: iteration 1226/ 3814 | consumed samples: 627712 | consumed tokens: 1285554176 | elapsed time per iteration (s): 6.10 | learning rate: 4.432E-04 | global batch size: 512 | lm loss: 3.954792E+00 | loss scale: 16384.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.912 | TFLOPs: 63.38 | +[default7]: iteration 1227/ 3814 | consumed samples: 628224 | consumed tokens: 1286602752 | elapsed time per iteration (s): 6.04 | learning rate: 4.430E-04 | global batch size: 512 | lm loss: 3.973904E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.768 | TFLOPs: 64.03 | +[default7]: iteration 1228/ 3814 | consumed samples: 628736 | consumed tokens: 1287651328 | elapsed time per iteration (s): 6.09 | learning rate: 4.428E-04 | global batch size: 512 | lm loss: 3.941539E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.022 | TFLOPs: 63.46 | +[default7]: iteration 1229/ 3814 | consumed samples: 629248 | consumed tokens: 1288699904 | elapsed time per iteration (s): 6.14 | learning rate: 4.427E-04 | global batch size: 512 | lm loss: 3.970738E+00 | loss scale: 16384.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.339 | TFLOPs: 62.95 | +[default7]: iteration 1230/ 3814 | consumed samples: 629760 | consumed tokens: 1289748480 | elapsed time per iteration (s): 6.01 | learning rate: 4.425E-04 | global batch size: 512 | lm loss: 3.965043E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.184 | TFLOPs: 64.34 | +[default7]: iteration 1231/ 3814 | consumed samples: 630272 | consumed tokens: 1290797056 | elapsed time per iteration (s): 6.09 | learning rate: 4.423E-04 | global batch size: 512 | lm loss: 3.941085E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.133 | TFLOPs: 63.55 | +[default7]: iteration 1232/ 3814 | consumed samples: 630784 | consumed tokens: 1291845632 | elapsed time per iteration (s): 5.93 | learning rate: 4.422E-04 | global batch size: 512 | lm loss: 3.968178E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.274 | TFLOPs: 65.16 | +[default7]: iteration 1233/ 3814 | consumed samples: 631296 | consumed tokens: 1292894208 | elapsed time per iteration (s): 6.12 | learning rate: 4.420E-04 | global batch size: 512 | lm loss: 3.962111E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.666 | TFLOPs: 63.19 | +[default7]: iteration 1234/ 3814 | consumed samples: 631808 | consumed tokens: 1293942784 | elapsed time per iteration (s): 6.18 | learning rate: 4.418E-04 | global batch size: 512 | lm loss: 3.938493E+00 | loss scale: 16384.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.893 | TFLOPs: 62.61 | +[default7]: iteration 1235/ 3814 | consumed samples: 632320 | consumed tokens: 1294991360 | elapsed time per iteration (s): 6.14 | learning rate: 4.416E-04 | global batch size: 512 | lm loss: 3.958409E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.398 | TFLOPs: 62.99 | +[default7]: iteration 1236/ 3814 | consumed samples: 632832 | consumed tokens: 1296039936 | elapsed time per iteration (s): 6.00 | learning rate: 4.415E-04 | global batch size: 512 | lm loss: 3.961909E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.385 | TFLOPs: 64.49 | +[default7]: iteration 1237/ 3814 | consumed samples: 633344 | consumed tokens: 1297088512 | elapsed time per iteration (s): 6.13 | learning rate: 4.413E-04 | global batch size: 512 | lm loss: 3.939124E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.478 | TFLOPs: 63.05 | +[default7]: iteration 1238/ 3814 | consumed samples: 633856 | consumed tokens: 1298137088 | elapsed time per iteration (s): 6.13 | learning rate: 4.411E-04 | global batch size: 512 | lm loss: 3.957904E+00 | loss scale: 16384.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.515 | TFLOPs: 63.08 | +[default7]: iteration 1239/ 3814 | consumed samples: 634368 | consumed tokens: 1299185664 | elapsed time per iteration (s): 6.22 | learning rate: 4.410E-04 | global batch size: 512 | lm loss: 3.929135E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.267 | TFLOPs: 62.14 | +[default7]: iteration 1240/ 3814 | consumed samples: 634880 | consumed tokens: 1300234240 | elapsed time per iteration (s): 6.12 | learning rate: 4.408E-04 | global batch size: 512 | lm loss: 3.965210E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.673 | TFLOPs: 63.20 | +[default7]: iteration 1241/ 3814 | consumed samples: 635392 | consumed tokens: 1301282816 | elapsed time per iteration (s): 6.17 | learning rate: 4.406E-04 | global batch size: 512 | lm loss: 3.929487E+00 | loss scale: 16384.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.917 | TFLOPs: 62.63 | +[default7]: iteration 1242/ 3814 | consumed samples: 635904 | consumed tokens: 1302331392 | elapsed time per iteration (s): 6.15 | learning rate: 4.405E-04 | global batch size: 512 | lm loss: 3.956575E+00 | loss scale: 16384.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.189 | TFLOPs: 62.83 | +[default7]: iteration 1243/ 3814 | consumed samples: 636416 | consumed tokens: 1303379968 | elapsed time per iteration (s): 5.93 | learning rate: 4.403E-04 | global batch size: 512 | lm loss: 3.973637E+00 | loss scale: 16384.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.382 | TFLOPs: 65.24 | +[default7]: iteration 1244/ 3814 | consumed samples: 636928 | consumed tokens: 1304428544 | elapsed time per iteration (s): 6.18 | learning rate: 4.401E-04 | global batch size: 512 | lm loss: 3.963040E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.841 | TFLOPs: 62.57 | +[default7]: iteration 1245/ 3814 | consumed samples: 637440 | consumed tokens: 1305477120 | elapsed time per iteration (s): 5.93 | learning rate: 4.399E-04 | global batch size: 512 | lm loss: 3.972198E+00 | loss scale: 16384.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.319 | TFLOPs: 65.20 | +[default7]: iteration 1246/ 3814 | consumed samples: 637952 | consumed tokens: 1306525696 | elapsed time per iteration (s): 6.20 | learning rate: 4.398E-04 | global batch size: 512 | lm loss: 3.954716E+00 | loss scale: 16384.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.517 | TFLOPs: 62.33 | +[default7]: iteration 1247/ 3814 | consumed samples: 638464 | consumed tokens: 1307574272 | elapsed time per iteration (s): 5.99 | learning rate: 4.396E-04 | global batch size: 512 | lm loss: 3.927456E+00 | loss scale: 16384.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.486 | TFLOPs: 64.57 | +[default7]: iteration 1248/ 3814 | consumed samples: 638976 | consumed tokens: 1308622848 | elapsed time per iteration (s): 6.04 | learning rate: 4.394E-04 | global batch size: 512 | lm loss: 3.962052E+00 | loss scale: 16384.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.825 | TFLOPs: 64.07 | +[default7]: iteration 1249/ 3814 | consumed samples: 639488 | consumed tokens: 1309671424 | elapsed time per iteration (s): 6.01 | learning rate: 4.393E-04 | global batch size: 512 | lm loss: 3.960588E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.239 | TFLOPs: 64.38 | +[default7]: iteration 1250/ 3814 | consumed samples: 640000 | consumed tokens: 1310720000 | elapsed time per iteration (s): 5.94 | learning rate: 4.391E-04 | global batch size: 512 | lm loss: 3.915587E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.259 | TFLOPs: 65.15 | +[default0]:saving checkpoint at iteration 1250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 09:37:34,206] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1250 is begin to save! +[default0]:[2023-02-16 09:37:34,209] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:34,209] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:34,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,364] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:34,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:34,369] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:34,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:34,432] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:34,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,418] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:34,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:34,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:34,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,475] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:34,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,531] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:34,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,652] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:34,704] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,705] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:34,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:34,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:34,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:34,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,848] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:34,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:34,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:34,904] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:34,905] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,074] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,073] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,074] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:35,153] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,154] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,154] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,155] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:35,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,218] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,213] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:35,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,267] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:35,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,329] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,323] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,386] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,387] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:35,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,443] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,379] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:35,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,565] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:35,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,730] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:35,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:35,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,847] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,786] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:35,844] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,845] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,907] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,908] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:35,903] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,904] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:35,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:35,963] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:35,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:35,968] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,028] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,029] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,021] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:36,084] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,084] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,141] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,076] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,076] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:36,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,133] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:36,195] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,252] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:36,244] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,245] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:36,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,311] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,306] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:36,363] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,363] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:36,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,367] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,426] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,421] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:36,489] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,490] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,475] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,476] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:36,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,531] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 09:37:36,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,555] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,611] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 09:37:36,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:36,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,649] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 09:37:36,649] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 09:37:36,651] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_01_model_states.pt +[default1]:[2023-02-16 09:37:36,651] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 09:37:36,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 09:37:36,666] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,667] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,720] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_00-model_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 09:37:36,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 09:37:36,783] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 09:37:36,784] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_00_model_states.pt +[default0]:[2023-02-16 09:37:36,784] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 09:37:36,787] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 09:37:36,824] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 09:37:37,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,341] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,341] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,378] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,380] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,378] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,422] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,393] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,401] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,401] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,469] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,374] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,374] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,382] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,382] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,382] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,423] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,423] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,423] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,460] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,460] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,444] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,444] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,444] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,428] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,486] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,486] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,425] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,425] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,510] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,445] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,445] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,450] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,451] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,441] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,441] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,515] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,515] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,494] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,512] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,512] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,557] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,557] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,519] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,519] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,519] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,529] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,558] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,494] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,495] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,495] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,495] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,511] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,512] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,512] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,570] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,517] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,517] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,544] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,544] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,581] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,581] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,573] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,573] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,552] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,609] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,609] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,575] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,616] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,616] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,616] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,604] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,605] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,605] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,558] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,558] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,558] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,648] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,648] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,648] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,592] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,592] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,592] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,589] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,589] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,589] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,580] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,590] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,591] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,593] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,593] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,610] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default2]:[2023-02-16 09:37:37,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 09:37:37,630] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 09:37:37,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default4]:[2023-02-16 09:37:37,747] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 09:37:37,747] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 09:37:37,747] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,714] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,714] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,722] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,722] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:37,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:37,729] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:37,729] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,732] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,764] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,764] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default1]:[2023-02-16 09:37:37,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 09:37:37,799] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 09:37:37,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default5]:[2023-02-16 09:37:37,750] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 09:37:37,750] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 09:37:37,751] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,797] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,797] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,797] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]:[2023-02-16 09:37:37,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 09:37:37,815] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 09:37:37,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,786] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,786] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default7]:[2023-02-16 09:37:37,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 09:37:37,820] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 09:37:37,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default6]:[2023-02-16 09:37:37,874] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 09:37:37,874] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 09:37:37,874] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default3]:[2023-02-16 09:37:38,140] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 09:37:38,141] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1250/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 09:37:38,141] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1250 is ready now! +[default0]: successfully saved checkpoint at iteration 1250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:time (ms) | save-checkpoint: 3936.31 +[default7]: iteration 1251/ 3814 | consumed samples: 640512 | consumed tokens: 1311768576 | elapsed time per iteration (s): 9.91 | learning rate: 4.389E-04 | global batch size: 512 | lm loss: 3.956403E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 51.670 | TFLOPs: 39.03 | +[default7]: iteration 1252/ 3814 | consumed samples: 641024 | consumed tokens: 1312817152 | elapsed time per iteration (s): 6.09 | learning rate: 4.387E-04 | global batch size: 512 | lm loss: 3.938971E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.116 | TFLOPs: 63.53 | +[default7]: iteration 1253/ 3814 | consumed samples: 641536 | consumed tokens: 1313865728 | elapsed time per iteration (s): 6.00 | learning rate: 4.386E-04 | global batch size: 512 | lm loss: 3.959106E+00 | loss scale: 16384.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.402 | TFLOPs: 64.51 | +[default7]: iteration 1254/ 3814 | consumed samples: 642048 | consumed tokens: 1314914304 | elapsed time per iteration (s): 5.97 | learning rate: 4.384E-04 | global batch size: 512 | lm loss: 3.974009E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.738 | TFLOPs: 64.76 | +[default7]: iteration 1255/ 3814 | consumed samples: 642560 | consumed tokens: 1315962880 | elapsed time per iteration (s): 6.05 | learning rate: 4.382E-04 | global batch size: 512 | lm loss: 3.924982E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.641 | TFLOPs: 63.93 | +[default7]: iteration 1256/ 3814 | consumed samples: 643072 | consumed tokens: 1317011456 | elapsed time per iteration (s): 5.92 | learning rate: 4.381E-04 | global batch size: 512 | lm loss: 3.914224E+00 | loss scale: 16384.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.548 | TFLOPs: 65.37 | +[default7]: iteration 1257/ 3814 | consumed samples: 643584 | consumed tokens: 1318060032 | elapsed time per iteration (s): 5.91 | learning rate: 4.379E-04 | global batch size: 512 | lm loss: 3.958304E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.686 | TFLOPs: 65.47 | +[default7]: iteration 1258/ 3814 | consumed samples: 644096 | consumed tokens: 1319108608 | elapsed time per iteration (s): 6.04 | learning rate: 4.377E-04 | global batch size: 512 | lm loss: 3.928230E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.809 | TFLOPs: 64.06 | +[default7]: iteration 1259/ 3814 | consumed samples: 644608 | consumed tokens: 1320157184 | elapsed time per iteration (s): 5.97 | learning rate: 4.375E-04 | global batch size: 512 | lm loss: 3.923157E+00 | loss scale: 16384.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.720 | TFLOPs: 64.75 | +[default7]: iteration 1260/ 3814 | consumed samples: 645120 | consumed tokens: 1321205760 | elapsed time per iteration (s): 6.02 | learning rate: 4.374E-04 | global batch size: 512 | lm loss: 3.897420E+00 | loss scale: 16384.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.023 | TFLOPs: 64.22 | +[default7]: iteration 1261/ 3814 | consumed samples: 645632 | consumed tokens: 1322254336 | elapsed time per iteration (s): 5.85 | learning rate: 4.372E-04 | global batch size: 512 | lm loss: 3.948893E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.558 | TFLOPs: 66.13 | +[default7]: iteration 1262/ 3814 | consumed samples: 646144 | consumed tokens: 1323302912 | elapsed time per iteration (s): 6.15 | learning rate: 4.370E-04 | global batch size: 512 | lm loss: 3.924245E+00 | loss scale: 16384.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.253 | TFLOPs: 62.88 | +[default7]: iteration 1263/ 3814 | consumed samples: 646656 | consumed tokens: 1324351488 | elapsed time per iteration (s): 6.11 | learning rate: 4.369E-04 | global batch size: 512 | lm loss: 3.952524E+00 | loss scale: 16384.0 | grad norm: 0.192 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.762 | TFLOPs: 63.27 | +[default7]: iteration 1264/ 3814 | consumed samples: 647168 | consumed tokens: 1325400064 | elapsed time per iteration (s): 6.17 | learning rate: 4.367E-04 | global batch size: 512 | lm loss: 3.934346E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.002 | TFLOPs: 62.69 | +[default7]: iteration 1265/ 3814 | consumed samples: 647680 | consumed tokens: 1326448640 | elapsed time per iteration (s): 6.16 | learning rate: 4.365E-04 | global batch size: 512 | lm loss: 3.944079E+00 | loss scale: 16384.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.117 | TFLOPs: 62.78 | +[default7]: iteration 1266/ 3814 | consumed samples: 648192 | consumed tokens: 1327497216 | elapsed time per iteration (s): 5.99 | learning rate: 4.363E-04 | global batch size: 512 | lm loss: 3.919432E+00 | loss scale: 16384.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.450 | TFLOPs: 64.54 | +[default7]: iteration 1267/ 3814 | consumed samples: 648704 | consumed tokens: 1328545792 | elapsed time per iteration (s): 5.99 | learning rate: 4.362E-04 | global batch size: 512 | lm loss: 3.910292E+00 | loss scale: 16384.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.489 | TFLOPs: 64.57 | +[default7]: iteration 1268/ 3814 | consumed samples: 649216 | consumed tokens: 1329594368 | elapsed time per iteration (s): 6.07 | learning rate: 4.360E-04 | global batch size: 512 | lm loss: 3.925926E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.349 | TFLOPs: 63.71 | +[default7]: iteration 1269/ 3814 | consumed samples: 649728 | consumed tokens: 1330642944 | elapsed time per iteration (s): 6.10 | learning rate: 4.358E-04 | global batch size: 512 | lm loss: 3.948030E+00 | loss scale: 16384.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.994 | TFLOPs: 63.44 | +[default7]: iteration 1270/ 3814 | consumed samples: 650240 | consumed tokens: 1331691520 | elapsed time per iteration (s): 5.98 | learning rate: 4.356E-04 | global batch size: 512 | lm loss: 3.936249E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.685 | TFLOPs: 64.72 | +[default7]: iteration 1271/ 3814 | consumed samples: 650752 | consumed tokens: 1332740096 | elapsed time per iteration (s): 5.97 | learning rate: 4.355E-04 | global batch size: 512 | lm loss: 3.906320E+00 | loss scale: 16384.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.804 | TFLOPs: 64.81 | +[default7]: iteration 1272/ 3814 | consumed samples: 651264 | consumed tokens: 1333788672 | elapsed time per iteration (s): 5.95 | learning rate: 4.353E-04 | global batch size: 512 | lm loss: 3.921326E+00 | loss scale: 16384.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.105 | TFLOPs: 65.04 | +[default7]: iteration 1273/ 3814 | consumed samples: 651776 | consumed tokens: 1334837248 | elapsed time per iteration (s): 6.01 | learning rate: 4.351E-04 | global batch size: 512 | lm loss: 3.923580E+00 | loss scale: 16384.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.233 | TFLOPs: 64.38 | +[default7]: iteration 1274/ 3814 | consumed samples: 652288 | consumed tokens: 1335885824 | elapsed time per iteration (s): 5.99 | learning rate: 4.349E-04 | global batch size: 512 | lm loss: 3.921389E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.538 | TFLOPs: 64.61 | +[default7]: iteration 1275/ 3814 | consumed samples: 652800 | consumed tokens: 1336934400 | elapsed time per iteration (s): 5.99 | learning rate: 4.348E-04 | global batch size: 512 | lm loss: 3.911175E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.490 | TFLOPs: 64.57 | +[default7]: iteration 1276/ 3814 | consumed samples: 653312 | consumed tokens: 1337982976 | elapsed time per iteration (s): 5.96 | learning rate: 4.346E-04 | global batch size: 512 | lm loss: 3.926075E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.897 | TFLOPs: 64.88 | +[default7]: iteration 1277/ 3814 | consumed samples: 653824 | consumed tokens: 1339031552 | elapsed time per iteration (s): 5.91 | learning rate: 4.344E-04 | global batch size: 512 | lm loss: 3.893031E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.656 | TFLOPs: 65.45 | +[default7]: iteration 1278/ 3814 | consumed samples: 654336 | consumed tokens: 1340080128 | elapsed time per iteration (s): 5.97 | learning rate: 4.342E-04 | global batch size: 512 | lm loss: 3.892254E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.701 | TFLOPs: 64.73 | +[default7]: iteration 1279/ 3814 | consumed samples: 654848 | consumed tokens: 1341128704 | elapsed time per iteration (s): 6.01 | learning rate: 4.341E-04 | global batch size: 512 | lm loss: 3.897961E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.247 | TFLOPs: 64.39 | +[default7]: iteration 1280/ 3814 | consumed samples: 655360 | consumed tokens: 1342177280 | elapsed time per iteration (s): 6.03 | learning rate: 4.339E-04 | global batch size: 512 | lm loss: 3.904504E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.885 | TFLOPs: 64.11 | +[default7]: iteration 1281/ 3814 | consumed samples: 655872 | consumed tokens: 1343225856 | elapsed time per iteration (s): 6.06 | learning rate: 4.337E-04 | global batch size: 512 | lm loss: 3.913637E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.458 | TFLOPs: 63.79 | +[default7]: iteration 1282/ 3814 | consumed samples: 656384 | consumed tokens: 1344274432 | elapsed time per iteration (s): 5.96 | learning rate: 4.335E-04 | global batch size: 512 | lm loss: 3.931481E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.872 | TFLOPs: 64.86 | +[default7]: iteration 1283/ 3814 | consumed samples: 656896 | consumed tokens: 1345323008 | elapsed time per iteration (s): 5.99 | learning rate: 4.334E-04 | global batch size: 512 | lm loss: 3.884882E+00 | loss scale: 16384.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.454 | TFLOPs: 64.54 | +[default7]: iteration 1284/ 3814 | consumed samples: 657408 | consumed tokens: 1346371584 | elapsed time per iteration (s): 5.96 | learning rate: 4.332E-04 | global batch size: 512 | lm loss: 3.926321E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.908 | TFLOPs: 64.89 | +[default7]: iteration 1285/ 3814 | consumed samples: 657920 | consumed tokens: 1347420160 | elapsed time per iteration (s): 5.97 | learning rate: 4.330E-04 | global batch size: 512 | lm loss: 3.898021E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.718 | TFLOPs: 64.74 | +[default7]: iteration 1286/ 3814 | consumed samples: 658432 | consumed tokens: 1348468736 | elapsed time per iteration (s): 6.03 | learning rate: 4.328E-04 | global batch size: 512 | lm loss: 3.905012E+00 | loss scale: 16384.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.909 | TFLOPs: 64.13 | +[default7]: iteration 1287/ 3814 | consumed samples: 658944 | consumed tokens: 1349517312 | elapsed time per iteration (s): 6.15 | learning rate: 4.327E-04 | global batch size: 512 | lm loss: 3.884101E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.319 | TFLOPs: 62.93 | +[default7]: iteration 1288/ 3814 | consumed samples: 659456 | consumed tokens: 1350565888 | elapsed time per iteration (s): 5.96 | learning rate: 4.325E-04 | global batch size: 512 | lm loss: 3.868178E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.899 | TFLOPs: 64.88 | +[default7]: iteration 1289/ 3814 | consumed samples: 659968 | consumed tokens: 1351614464 | elapsed time per iteration (s): 5.99 | learning rate: 4.323E-04 | global batch size: 512 | lm loss: 3.898054E+00 | loss scale: 16384.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.523 | TFLOPs: 64.60 | +[default7]: iteration 1290/ 3814 | consumed samples: 660480 | consumed tokens: 1352663040 | elapsed time per iteration (s): 6.04 | learning rate: 4.321E-04 | global batch size: 512 | lm loss: 3.873648E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.731 | TFLOPs: 64.00 | +[default7]: iteration 1291/ 3814 | consumed samples: 660992 | consumed tokens: 1353711616 | elapsed time per iteration (s): 5.94 | learning rate: 4.319E-04 | global batch size: 512 | lm loss: 3.886523E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.177 | TFLOPs: 65.09 | +[default7]: iteration 1292/ 3814 | consumed samples: 661504 | consumed tokens: 1354760192 | elapsed time per iteration (s): 6.04 | learning rate: 4.318E-04 | global batch size: 512 | lm loss: 3.897376E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.735 | TFLOPs: 64.00 | +[default7]: iteration 1293/ 3814 | consumed samples: 662016 | consumed tokens: 1355808768 | elapsed time per iteration (s): 5.99 | learning rate: 4.316E-04 | global batch size: 512 | lm loss: 3.851175E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.428 | TFLOPs: 64.52 | +[default7]: iteration 1294/ 3814 | consumed samples: 662528 | consumed tokens: 1356857344 | elapsed time per iteration (s): 5.98 | learning rate: 4.314E-04 | global batch size: 512 | lm loss: 3.893395E+00 | loss scale: 16384.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.648 | TFLOPs: 64.69 | +[default7]: iteration 1295/ 3814 | consumed samples: 663040 | consumed tokens: 1357905920 | elapsed time per iteration (s): 6.01 | learning rate: 4.312E-04 | global batch size: 512 | lm loss: 3.906633E+00 | loss scale: 16384.0 | grad norm: 0.188 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.150 | TFLOPs: 64.31 | +[default7]: iteration 1296/ 3814 | consumed samples: 663552 | consumed tokens: 1358954496 | elapsed time per iteration (s): 5.93 | learning rate: 4.311E-04 | global batch size: 512 | lm loss: 3.891536E+00 | loss scale: 16384.0 | grad norm: 0.202 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.329 | TFLOPs: 65.20 | +[default7]: iteration 1297/ 3814 | consumed samples: 664064 | consumed tokens: 1360003072 | elapsed time per iteration (s): 6.01 | learning rate: 4.309E-04 | global batch size: 512 | lm loss: 3.891189E+00 | loss scale: 16384.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.127 | TFLOPs: 64.30 | +[default7]: iteration 1298/ 3814 | consumed samples: 664576 | consumed tokens: 1361051648 | elapsed time per iteration (s): 5.97 | learning rate: 4.307E-04 | global batch size: 512 | lm loss: 3.916351E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.813 | TFLOPs: 64.82 | +[default7]: iteration 1299/ 3814 | consumed samples: 665088 | consumed tokens: 1362100224 | elapsed time per iteration (s): 5.99 | learning rate: 4.305E-04 | global batch size: 512 | lm loss: 3.909544E+00 | loss scale: 16384.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.442 | TFLOPs: 64.54 | +[default7]: iteration 1300/ 3814 | consumed samples: 665600 | consumed tokens: 1363148800 | elapsed time per iteration (s): 6.01 | learning rate: 4.303E-04 | global batch size: 512 | lm loss: 3.862741E+00 | loss scale: 16384.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.151 | TFLOPs: 64.32 | +[default7]: iteration 1301/ 3814 | consumed samples: 666112 | consumed tokens: 1364197376 | elapsed time per iteration (s): 5.96 | learning rate: 4.302E-04 | global batch size: 512 | lm loss: 3.878186E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.901 | TFLOPs: 64.88 | +[default7]: iteration 1302/ 3814 | consumed samples: 666624 | consumed tokens: 1365245952 | elapsed time per iteration (s): 5.87 | learning rate: 4.300E-04 | global batch size: 512 | lm loss: 3.879282E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.203 | TFLOPs: 65.87 | +[default7]: iteration 1303/ 3814 | consumed samples: 667136 | consumed tokens: 1366294528 | elapsed time per iteration (s): 5.99 | learning rate: 4.298E-04 | global batch size: 512 | lm loss: 3.906729E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.521 | TFLOPs: 64.59 | +[default7]: iteration 1304/ 3814 | consumed samples: 667648 | consumed tokens: 1367343104 | elapsed time per iteration (s): 5.99 | learning rate: 4.296E-04 | global batch size: 512 | lm loss: 3.887084E+00 | loss scale: 16384.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.507 | TFLOPs: 64.58 | +[default7]: iteration 1305/ 3814 | consumed samples: 668160 | consumed tokens: 1368391680 | elapsed time per iteration (s): 6.00 | learning rate: 4.295E-04 | global batch size: 512 | lm loss: 3.876487E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.340 | TFLOPs: 64.46 | +[default7]: iteration 1306/ 3814 | consumed samples: 668672 | consumed tokens: 1369440256 | elapsed time per iteration (s): 5.91 | learning rate: 4.293E-04 | global batch size: 512 | lm loss: 3.868752E+00 | loss scale: 16384.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.630 | TFLOPs: 65.43 | +[default7]: iteration 1307/ 3814 | consumed samples: 669184 | consumed tokens: 1370488832 | elapsed time per iteration (s): 6.02 | learning rate: 4.291E-04 | global batch size: 512 | lm loss: 3.851934E+00 | loss scale: 16384.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.085 | TFLOPs: 64.27 | +[default7]: iteration 1308/ 3814 | consumed samples: 669696 | consumed tokens: 1371537408 | elapsed time per iteration (s): 5.95 | learning rate: 4.289E-04 | global batch size: 512 | lm loss: 3.860086E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.065 | TFLOPs: 65.01 | +[default7]: iteration 1309/ 3814 | consumed samples: 670208 | consumed tokens: 1372585984 | elapsed time per iteration (s): 6.03 | learning rate: 4.287E-04 | global batch size: 512 | lm loss: 3.869168E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.911 | TFLOPs: 64.13 | +[default7]: iteration 1310/ 3814 | consumed samples: 670720 | consumed tokens: 1373634560 | elapsed time per iteration (s): 6.01 | learning rate: 4.286E-04 | global batch size: 512 | lm loss: 3.924212E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.240 | TFLOPs: 64.38 | +[default7]: iteration 1311/ 3814 | consumed samples: 671232 | consumed tokens: 1374683136 | elapsed time per iteration (s): 6.00 | learning rate: 4.284E-04 | global batch size: 512 | lm loss: 3.863780E+00 | loss scale: 16384.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.280 | TFLOPs: 64.41 | +[default7]: iteration 1312/ 3814 | consumed samples: 671744 | consumed tokens: 1375731712 | elapsed time per iteration (s): 6.02 | learning rate: 4.282E-04 | global batch size: 512 | lm loss: 3.873300E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.016 | TFLOPs: 64.21 | +[default7]: iteration 1313/ 3814 | consumed samples: 672256 | consumed tokens: 1376780288 | elapsed time per iteration (s): 6.00 | learning rate: 4.280E-04 | global batch size: 512 | lm loss: 3.900337E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.402 | TFLOPs: 64.51 | +[default7]: iteration 1314/ 3814 | consumed samples: 672768 | consumed tokens: 1377828864 | elapsed time per iteration (s): 5.98 | learning rate: 4.278E-04 | global batch size: 512 | lm loss: 3.885531E+00 | loss scale: 16384.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.681 | TFLOPs: 64.72 | +[default7]: iteration 1315/ 3814 | consumed samples: 673280 | consumed tokens: 1378877440 | elapsed time per iteration (s): 5.97 | learning rate: 4.277E-04 | global batch size: 512 | lm loss: 3.864192E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.762 | TFLOPs: 64.78 | +[default7]: iteration 1316/ 3814 | consumed samples: 673792 | consumed tokens: 1379926016 | elapsed time per iteration (s): 5.94 | learning rate: 4.275E-04 | global batch size: 512 | lm loss: 3.845527E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.124 | TFLOPs: 65.05 | +[default7]: iteration 1317/ 3814 | consumed samples: 674304 | consumed tokens: 1380974592 | elapsed time per iteration (s): 5.94 | learning rate: 4.273E-04 | global batch size: 512 | lm loss: 3.871333E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.236 | TFLOPs: 65.14 | +[default7]: iteration 1318/ 3814 | consumed samples: 674816 | consumed tokens: 1382023168 | elapsed time per iteration (s): 5.97 | learning rate: 4.271E-04 | global batch size: 512 | lm loss: 3.889116E+00 | loss scale: 16384.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.722 | TFLOPs: 64.75 | +[default7]: iteration 1319/ 3814 | consumed samples: 675328 | consumed tokens: 1383071744 | elapsed time per iteration (s): 5.94 | learning rate: 4.269E-04 | global batch size: 512 | lm loss: 3.871980E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.135 | TFLOPs: 65.06 | +[default7]: iteration 1320/ 3814 | consumed samples: 675840 | consumed tokens: 1384120320 | elapsed time per iteration (s): 6.00 | learning rate: 4.267E-04 | global batch size: 512 | lm loss: 3.863354E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.337 | TFLOPs: 64.46 | +[default7]: iteration 1321/ 3814 | consumed samples: 676352 | consumed tokens: 1385168896 | elapsed time per iteration (s): 5.98 | learning rate: 4.266E-04 | global batch size: 512 | lm loss: 3.858135E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.552 | TFLOPs: 64.62 | +[default7]: iteration 1322/ 3814 | consumed samples: 676864 | consumed tokens: 1386217472 | elapsed time per iteration (s): 6.04 | learning rate: 4.264E-04 | global batch size: 512 | lm loss: 3.871781E+00 | loss scale: 16384.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.725 | TFLOPs: 63.99 | +[default7]: iteration 1323/ 3814 | consumed samples: 677376 | consumed tokens: 1387266048 | elapsed time per iteration (s): 6.00 | learning rate: 4.262E-04 | global batch size: 512 | lm loss: 3.850365E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.275 | TFLOPs: 64.41 | +[default7]: iteration 1324/ 3814 | consumed samples: 677888 | consumed tokens: 1388314624 | elapsed time per iteration (s): 5.99 | learning rate: 4.260E-04 | global batch size: 512 | lm loss: 3.877678E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.432 | TFLOPs: 64.53 | +[default7]: iteration 1325/ 3814 | consumed samples: 678400 | consumed tokens: 1389363200 | elapsed time per iteration (s): 6.06 | learning rate: 4.258E-04 | global batch size: 512 | lm loss: 3.846231E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.431 | TFLOPs: 63.77 | +[default7]: iteration 1326/ 3814 | consumed samples: 678912 | consumed tokens: 1390411776 | elapsed time per iteration (s): 6.09 | learning rate: 4.257E-04 | global batch size: 512 | lm loss: 3.880133E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.051 | TFLOPs: 63.48 | +[default7]: iteration 1327/ 3814 | consumed samples: 679424 | consumed tokens: 1391460352 | elapsed time per iteration (s): 6.01 | learning rate: 4.255E-04 | global batch size: 512 | lm loss: 3.850922E+00 | loss scale: 16384.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.138 | TFLOPs: 64.31 | +[default7]: iteration 1328/ 3814 | consumed samples: 679936 | consumed tokens: 1392508928 | elapsed time per iteration (s): 5.95 | learning rate: 4.253E-04 | global batch size: 512 | lm loss: 3.859964E+00 | loss scale: 16384.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.113 | TFLOPs: 65.04 | +[default7]: iteration 1329/ 3814 | consumed samples: 680448 | consumed tokens: 1393557504 | elapsed time per iteration (s): 5.97 | learning rate: 4.251E-04 | global batch size: 512 | lm loss: 3.889922E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.733 | TFLOPs: 64.75 | +[default7]: iteration 1330/ 3814 | consumed samples: 680960 | consumed tokens: 1394606080 | elapsed time per iteration (s): 5.99 | learning rate: 4.249E-04 | global batch size: 512 | lm loss: 3.870898E+00 | loss scale: 16384.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.428 | TFLOPs: 64.52 | +[default7]: iteration 1331/ 3814 | consumed samples: 681472 | consumed tokens: 1395654656 | elapsed time per iteration (s): 5.96 | learning rate: 4.247E-04 | global batch size: 512 | lm loss: 3.875225E+00 | loss scale: 16384.0 | grad norm: 0.194 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.891 | TFLOPs: 64.87 | +[default7]: iteration 1332/ 3814 | consumed samples: 681984 | consumed tokens: 1396703232 | elapsed time per iteration (s): 5.98 | learning rate: 4.246E-04 | global batch size: 512 | lm loss: 3.865419E+00 | loss scale: 16384.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.639 | TFLOPs: 64.68 | +[default7]: iteration 1333/ 3814 | consumed samples: 682496 | consumed tokens: 1397751808 | elapsed time per iteration (s): 5.99 | learning rate: 4.244E-04 | global batch size: 512 | lm loss: 3.823830E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.513 | TFLOPs: 64.59 | +[default7]: iteration 1334/ 3814 | consumed samples: 683008 | consumed tokens: 1398800384 | elapsed time per iteration (s): 5.96 | learning rate: 4.242E-04 | global batch size: 512 | lm loss: 3.855522E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.925 | TFLOPs: 64.90 | +[default7]: iteration 1335/ 3814 | consumed samples: 683520 | consumed tokens: 1399848960 | elapsed time per iteration (s): 5.95 | learning rate: 4.240E-04 | global batch size: 512 | lm loss: 3.863006E+00 | loss scale: 16384.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.116 | TFLOPs: 65.04 | +[default7]: iteration 1336/ 3814 | consumed samples: 684032 | consumed tokens: 1400897536 | elapsed time per iteration (s): 6.01 | learning rate: 4.238E-04 | global batch size: 512 | lm loss: 3.856324E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.151 | TFLOPs: 64.32 | +[default7]: iteration 1337/ 3814 | consumed samples: 684544 | consumed tokens: 1401946112 | elapsed time per iteration (s): 6.08 | learning rate: 4.236E-04 | global batch size: 512 | lm loss: 3.846457E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.252 | TFLOPs: 63.64 | +[default7]: iteration 1338/ 3814 | consumed samples: 685056 | consumed tokens: 1402994688 | elapsed time per iteration (s): 6.07 | learning rate: 4.235E-04 | global batch size: 512 | lm loss: 3.813645E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.327 | TFLOPs: 63.69 | +[default7]: iteration 1339/ 3814 | consumed samples: 685568 | consumed tokens: 1404043264 | elapsed time per iteration (s): 6.00 | learning rate: 4.233E-04 | global batch size: 512 | lm loss: 3.848013E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.378 | TFLOPs: 64.49 | +[default7]: iteration 1340/ 3814 | consumed samples: 686080 | consumed tokens: 1405091840 | elapsed time per iteration (s): 5.97 | learning rate: 4.231E-04 | global batch size: 512 | lm loss: 3.887352E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.703 | TFLOPs: 64.73 | +[default7]: iteration 1341/ 3814 | consumed samples: 686592 | consumed tokens: 1406140416 | elapsed time per iteration (s): 6.01 | learning rate: 4.229E-04 | global batch size: 512 | lm loss: 3.859564E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.244 | TFLOPs: 64.39 | +[default7]: iteration 1342/ 3814 | consumed samples: 687104 | consumed tokens: 1407188992 | elapsed time per iteration (s): 6.01 | learning rate: 4.227E-04 | global batch size: 512 | lm loss: 3.843879E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.121 | TFLOPs: 64.29 | +[default7]: iteration 1343/ 3814 | consumed samples: 687616 | consumed tokens: 1408237568 | elapsed time per iteration (s): 5.97 | learning rate: 4.225E-04 | global batch size: 512 | lm loss: 3.850405E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.710 | TFLOPs: 64.74 | +[default7]: iteration 1344/ 3814 | consumed samples: 688128 | consumed tokens: 1409286144 | elapsed time per iteration (s): 5.93 | learning rate: 4.224E-04 | global batch size: 512 | lm loss: 3.826308E+00 | loss scale: 16384.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.301 | TFLOPs: 65.18 | +[default7]: iteration 1345/ 3814 | consumed samples: 688640 | consumed tokens: 1410334720 | elapsed time per iteration (s): 6.02 | learning rate: 4.222E-04 | global batch size: 512 | lm loss: 3.845304E+00 | loss scale: 16384.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.041 | TFLOPs: 64.23 | +[default7]: iteration 1346/ 3814 | consumed samples: 689152 | consumed tokens: 1411383296 | elapsed time per iteration (s): 5.95 | learning rate: 4.220E-04 | global batch size: 512 | lm loss: 3.855930E+00 | loss scale: 16384.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.030 | TFLOPs: 64.98 | +[default7]: iteration 1347/ 3814 | consumed samples: 689664 | consumed tokens: 1412431872 | elapsed time per iteration (s): 5.97 | learning rate: 4.218E-04 | global batch size: 512 | lm loss: 3.812674E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.825 | TFLOPs: 64.82 | +[default7]: iteration 1348/ 3814 | consumed samples: 690176 | consumed tokens: 1413480448 | elapsed time per iteration (s): 6.01 | learning rate: 4.216E-04 | global batch size: 512 | lm loss: 3.856519E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.187 | TFLOPs: 64.34 | +[default7]: iteration 1349/ 3814 | consumed samples: 690688 | consumed tokens: 1414529024 | elapsed time per iteration (s): 5.98 | learning rate: 4.214E-04 | global batch size: 512 | lm loss: 3.845190E+00 | loss scale: 16384.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 1350/ 3814 | consumed samples: 691200 | consumed tokens: 1415577600 | elapsed time per iteration (s): 5.97 | learning rate: 4.212E-04 | global batch size: 512 | lm loss: 3.833249E+00 | loss scale: 16384.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.770 | TFLOPs: 64.78 | +[default7]: iteration 1351/ 3814 | consumed samples: 691712 | consumed tokens: 1416626176 | elapsed time per iteration (s): 6.06 | learning rate: 4.211E-04 | global batch size: 512 | lm loss: 3.867890E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.540 | TFLOPs: 63.85 | +[default7]: iteration 1352/ 3814 | consumed samples: 692224 | consumed tokens: 1417674752 | elapsed time per iteration (s): 6.03 | learning rate: 4.209E-04 | global batch size: 512 | lm loss: 3.840046E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.848 | TFLOPs: 64.09 | +[default7]: iteration 1353/ 3814 | consumed samples: 692736 | consumed tokens: 1418723328 | elapsed time per iteration (s): 6.06 | learning rate: 4.207E-04 | global batch size: 512 | lm loss: 3.847146E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.544 | TFLOPs: 63.86 | +[default7]: iteration 1354/ 3814 | consumed samples: 693248 | consumed tokens: 1419771904 | elapsed time per iteration (s): 5.96 | learning rate: 4.205E-04 | global batch size: 512 | lm loss: 3.852629E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.937 | TFLOPs: 64.91 | +[default7]: iteration 1355/ 3814 | consumed samples: 693760 | consumed tokens: 1420820480 | elapsed time per iteration (s): 6.02 | learning rate: 4.203E-04 | global batch size: 512 | lm loss: 3.839804E+00 | loss scale: 16384.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.093 | TFLOPs: 64.27 | +[default7]: iteration 1356/ 3814 | consumed samples: 694272 | consumed tokens: 1421869056 | elapsed time per iteration (s): 5.87 | learning rate: 4.201E-04 | global batch size: 512 | lm loss: 3.838355E+00 | loss scale: 16384.0 | grad norm: 0.201 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.171 | TFLOPs: 65.84 | +[default7]: iteration 1357/ 3814 | consumed samples: 694784 | consumed tokens: 1422917632 | elapsed time per iteration (s): 6.00 | learning rate: 4.199E-04 | global batch size: 512 | lm loss: 3.840933E+00 | loss scale: 16384.0 | grad norm: 0.208 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.371 | TFLOPs: 64.48 | +[default7]: iteration 1358/ 3814 | consumed samples: 695296 | consumed tokens: 1423966208 | elapsed time per iteration (s): 5.92 | learning rate: 4.198E-04 | global batch size: 512 | lm loss: 3.828570E+00 | loss scale: 16384.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.471 | TFLOPs: 65.31 | +[default7]: iteration 1359/ 3814 | consumed samples: 695808 | consumed tokens: 1425014784 | elapsed time per iteration (s): 6.02 | learning rate: 4.196E-04 | global batch size: 512 | lm loss: 3.857118E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.044 | TFLOPs: 64.23 | +[default7]: iteration 1360/ 3814 | consumed samples: 696320 | consumed tokens: 1426063360 | elapsed time per iteration (s): 6.02 | learning rate: 4.194E-04 | global batch size: 512 | lm loss: 3.830490E+00 | loss scale: 16384.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.113 | TFLOPs: 64.29 | +[default7]: iteration 1361/ 3814 | consumed samples: 696832 | consumed tokens: 1427111936 | elapsed time per iteration (s): 5.97 | learning rate: 4.192E-04 | global batch size: 512 | lm loss: 3.845918E+00 | loss scale: 16384.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.760 | TFLOPs: 64.78 | +[default7]: iteration 1362/ 3814 | consumed samples: 697344 | consumed tokens: 1428160512 | elapsed time per iteration (s): 6.01 | learning rate: 4.190E-04 | global batch size: 512 | lm loss: 3.835426E+00 | loss scale: 16384.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.151 | TFLOPs: 64.32 | +[default7]: iteration 1363/ 3814 | consumed samples: 697856 | consumed tokens: 1429209088 | elapsed time per iteration (s): 6.02 | learning rate: 4.188E-04 | global batch size: 512 | lm loss: 3.822404E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.083 | TFLOPs: 64.26 | +[default7]: iteration 1364/ 3814 | consumed samples: 698368 | consumed tokens: 1430257664 | elapsed time per iteration (s): 5.98 | learning rate: 4.186E-04 | global batch size: 512 | lm loss: 3.836362E+00 | loss scale: 16384.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.548 | TFLOPs: 64.62 | +[default7]: iteration 1365/ 3814 | consumed samples: 698880 | consumed tokens: 1431306240 | elapsed time per iteration (s): 6.01 | learning rate: 4.185E-04 | global batch size: 512 | lm loss: 3.842560E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.164 | TFLOPs: 64.32 | +[default7]: iteration 1366/ 3814 | consumed samples: 699392 | consumed tokens: 1432354816 | elapsed time per iteration (s): 6.04 | learning rate: 4.183E-04 | global batch size: 512 | lm loss: 3.829476E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.772 | TFLOPs: 64.03 | +[default7]: iteration 1367/ 3814 | consumed samples: 699904 | consumed tokens: 1433403392 | elapsed time per iteration (s): 6.02 | learning rate: 4.181E-04 | global batch size: 512 | lm loss: 3.815188E+00 | loss scale: 16384.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.077 | TFLOPs: 64.26 | +[default7]: iteration 1368/ 3814 | consumed samples: 700416 | consumed tokens: 1434451968 | elapsed time per iteration (s): 6.02 | learning rate: 4.179E-04 | global batch size: 512 | lm loss: 3.840847E+00 | loss scale: 16384.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.119 | TFLOPs: 64.29 | +[default7]: iteration 1369/ 3814 | consumed samples: 700928 | consumed tokens: 1435500544 | elapsed time per iteration (s): 5.97 | learning rate: 4.177E-04 | global batch size: 512 | lm loss: 3.835756E+00 | loss scale: 16384.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.755 | TFLOPs: 64.77 | +[default7]: iteration 1370/ 3814 | consumed samples: 701440 | consumed tokens: 1436549120 | elapsed time per iteration (s): 5.99 | learning rate: 4.175E-04 | global batch size: 512 | lm loss: 3.809625E+00 | loss scale: 16384.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.540 | TFLOPs: 64.61 | +[default7]: iteration 1371/ 3814 | consumed samples: 701952 | consumed tokens: 1437597696 | elapsed time per iteration (s): 5.99 | learning rate: 4.173E-04 | global batch size: 512 | lm loss: 3.802872E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.484 | TFLOPs: 64.57 | +[default7]: iteration 1372/ 3814 | consumed samples: 702464 | consumed tokens: 1438646272 | elapsed time per iteration (s): 5.97 | learning rate: 4.171E-04 | global batch size: 512 | lm loss: 3.818399E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.781 | TFLOPs: 64.79 | +[default7]: iteration 1373/ 3814 | consumed samples: 702976 | consumed tokens: 1439694848 | elapsed time per iteration (s): 5.97 | learning rate: 4.170E-04 | global batch size: 512 | lm loss: 3.807148E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.826 | TFLOPs: 64.83 | +[default7]: iteration 1374/ 3814 | consumed samples: 703488 | consumed tokens: 1440743424 | elapsed time per iteration (s): 6.10 | learning rate: 4.168E-04 | global batch size: 512 | lm loss: 3.797942E+00 | loss scale: 16384.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.932 | TFLOPs: 63.39 | +[default7]: iteration 1375/ 3814 | consumed samples: 704000 | consumed tokens: 1441792000 | elapsed time per iteration (s): 6.04 | learning rate: 4.166E-04 | global batch size: 512 | lm loss: 3.837402E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.751 | TFLOPs: 64.01 | +[default7]: iteration 1376/ 3814 | consumed samples: 704512 | consumed tokens: 1442840576 | elapsed time per iteration (s): 6.03 | learning rate: 4.164E-04 | global batch size: 512 | lm loss: 3.829818E+00 | loss scale: 16384.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.909 | TFLOPs: 64.13 | +[default7]: iteration 1377/ 3814 | consumed samples: 705024 | consumed tokens: 1443889152 | elapsed time per iteration (s): 5.99 | learning rate: 4.162E-04 | global batch size: 512 | lm loss: 3.833359E+00 | loss scale: 16384.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.482 | TFLOPs: 64.57 | +[default7]: iteration 1378/ 3814 | consumed samples: 705536 | consumed tokens: 1444937728 | elapsed time per iteration (s): 6.01 | learning rate: 4.160E-04 | global batch size: 512 | lm loss: 3.810500E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.130 | TFLOPs: 64.30 | +[default7]: iteration 1379/ 3814 | consumed samples: 706048 | consumed tokens: 1445986304 | elapsed time per iteration (s): 5.99 | learning rate: 4.158E-04 | global batch size: 512 | lm loss: 3.851044E+00 | loss scale: 16384.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.495 | TFLOPs: 64.58 | +[default7]: iteration 1380/ 3814 | consumed samples: 706560 | consumed tokens: 1447034880 | elapsed time per iteration (s): 5.99 | learning rate: 4.156E-04 | global batch size: 512 | lm loss: 3.794570E+00 | loss scale: 16384.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.452 | TFLOPs: 64.54 | +[default7]: iteration 1381/ 3814 | consumed samples: 707072 | consumed tokens: 1448083456 | elapsed time per iteration (s): 5.99 | learning rate: 4.154E-04 | global batch size: 512 | lm loss: 3.800678E+00 | loss scale: 16384.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.413 | TFLOPs: 64.51 | +[default7]: iteration 1382/ 3814 | consumed samples: 707584 | consumed tokens: 1449132032 | elapsed time per iteration (s): 5.99 | learning rate: 4.153E-04 | global batch size: 512 | lm loss: 3.806210E+00 | loss scale: 16384.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.485 | TFLOPs: 64.57 | +[default7]: iteration 1383/ 3814 | consumed samples: 708096 | consumed tokens: 1450180608 | elapsed time per iteration (s): 6.00 | learning rate: 4.151E-04 | global batch size: 512 | lm loss: 3.813150E+00 | loss scale: 16384.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.383 | TFLOPs: 64.49 | +[default7]: iteration 1384/ 3814 | consumed samples: 708608 | consumed tokens: 1451229184 | elapsed time per iteration (s): 5.98 | learning rate: 4.149E-04 | global batch size: 512 | lm loss: 3.798395E+00 | loss scale: 16384.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.623 | TFLOPs: 64.67 | +[default7]: iteration 1385/ 3814 | consumed samples: 709120 | consumed tokens: 1452277760 | elapsed time per iteration (s): 5.96 | learning rate: 4.147E-04 | global batch size: 512 | lm loss: 3.818874E+00 | loss scale: 16384.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.867 | TFLOPs: 64.86 | +[default7]: iteration 1386/ 3814 | consumed samples: 709632 | consumed tokens: 1453326336 | elapsed time per iteration (s): 6.06 | learning rate: 4.145E-04 | global batch size: 512 | lm loss: 3.808901E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.550 | TFLOPs: 63.86 | +[default7]: iteration 1387/ 3814 | consumed samples: 710144 | consumed tokens: 1454374912 | elapsed time per iteration (s): 5.87 | learning rate: 4.143E-04 | global batch size: 512 | lm loss: 3.839877E+00 | loss scale: 16384.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.174 | TFLOPs: 65.84 | +[default7]: iteration 1388/ 3814 | consumed samples: 710656 | consumed tokens: 1455423488 | elapsed time per iteration (s): 6.06 | learning rate: 4.141E-04 | global batch size: 512 | lm loss: 3.795709E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.555 | TFLOPs: 63.87 | +[default7]: iteration 1389/ 3814 | consumed samples: 711168 | consumed tokens: 1456472064 | elapsed time per iteration (s): 5.92 | learning rate: 4.139E-04 | global batch size: 512 | lm loss: 3.827383E+00 | loss scale: 16384.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.432 | TFLOPs: 65.28 | +[default7]: iteration 1390/ 3814 | consumed samples: 711680 | consumed tokens: 1457520640 | elapsed time per iteration (s): 6.02 | learning rate: 4.137E-04 | global batch size: 512 | lm loss: 3.799670E+00 | loss scale: 16384.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.118 | TFLOPs: 64.29 | +[default7]: iteration 1391/ 3814 | consumed samples: 712192 | consumed tokens: 1458569216 | elapsed time per iteration (s): 6.06 | learning rate: 4.135E-04 | global batch size: 512 | lm loss: 3.799778E+00 | loss scale: 16384.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.420 | TFLOPs: 63.76 | +[default7]: iteration 1392/ 3814 | consumed samples: 712704 | consumed tokens: 1459617792 | elapsed time per iteration (s): 5.97 | learning rate: 4.133E-04 | global batch size: 512 | lm loss: 3.778953E+00 | loss scale: 16384.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.723 | TFLOPs: 64.75 | +[default7]: iteration 1393/ 3814 | consumed samples: 713216 | consumed tokens: 1460666368 | elapsed time per iteration (s): 5.99 | learning rate: 4.132E-04 | global batch size: 512 | lm loss: 3.817597E+00 | loss scale: 16384.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.457 | TFLOPs: 64.55 | +[default7]: iteration 1394/ 3814 | consumed samples: 713728 | consumed tokens: 1461714944 | elapsed time per iteration (s): 5.96 | learning rate: 4.130E-04 | global batch size: 512 | lm loss: 3.799268E+00 | loss scale: 16384.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.874 | TFLOPs: 64.86 | +[default7]: iteration 1395/ 3814 | consumed samples: 714240 | consumed tokens: 1462763520 | elapsed time per iteration (s): 5.99 | learning rate: 4.128E-04 | global batch size: 512 | lm loss: 3.803059E+00 | loss scale: 16384.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.430 | TFLOPs: 64.53 | +[default7]: iteration 1396/ 3814 | consumed samples: 714752 | consumed tokens: 1463812096 | elapsed time per iteration (s): 5.93 | learning rate: 4.126E-04 | global batch size: 512 | lm loss: 3.770360E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.383 | TFLOPs: 65.25 | +[default7]: iteration 1397/ 3814 | consumed samples: 715264 | consumed tokens: 1464860672 | elapsed time per iteration (s): 6.02 | learning rate: 4.124E-04 | global batch size: 512 | lm loss: 3.822817E+00 | loss scale: 16384.0 | grad norm: 0.185 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.023 | TFLOPs: 64.22 | +[default7]: iteration 1398/ 3814 | consumed samples: 715776 | consumed tokens: 1465909248 | elapsed time per iteration (s): 5.95 | learning rate: 4.122E-04 | global batch size: 512 | lm loss: 3.810766E+00 | loss scale: 16384.0 | grad norm: 0.204 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.080 | TFLOPs: 65.02 | +[default7]: iteration 1399/ 3814 | consumed samples: 716288 | consumed tokens: 1466957824 | elapsed time per iteration (s): 5.95 | learning rate: 4.120E-04 | global batch size: 512 | lm loss: 3.778609E+00 | loss scale: 16384.0 | grad norm: 0.174 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.992 | TFLOPs: 64.95 | +[default7]: iteration 1400/ 3814 | consumed samples: 716800 | consumed tokens: 1468006400 | elapsed time per iteration (s): 5.96 | learning rate: 4.118E-04 | global batch size: 512 | lm loss: 3.789990E+00 | loss scale: 16384.0 | grad norm: 0.162 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.864 | TFLOPs: 64.85 | +[default7]: iteration 1401/ 3814 | consumed samples: 717312 | consumed tokens: 1469054976 | elapsed time per iteration (s): 6.02 | learning rate: 4.116E-04 | global batch size: 512 | lm loss: 3.799334E+00 | loss scale: 16384.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.986 | TFLOPs: 64.19 | +[default7]: iteration 1402/ 3814 | consumed samples: 717824 | consumed tokens: 1470103552 | elapsed time per iteration (s): 5.97 | learning rate: 4.114E-04 | global batch size: 512 | lm loss: 3.811585E+00 | loss scale: 16384.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.799 | TFLOPs: 64.80 | +[default7]: iteration 1403/ 3814 | consumed samples: 718336 | consumed tokens: 1471152128 | elapsed time per iteration (s): 6.03 | learning rate: 4.112E-04 | global batch size: 512 | lm loss: 3.803689E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.852 | TFLOPs: 64.09 | +[default7]: iteration 1404/ 3814 | consumed samples: 718848 | consumed tokens: 1472200704 | elapsed time per iteration (s): 5.95 | learning rate: 4.111E-04 | global batch size: 512 | lm loss: 3.802887E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.052 | TFLOPs: 65.00 | +[default7]: iteration 1405/ 3814 | consumed samples: 719360 | consumed tokens: 1473249280 | elapsed time per iteration (s): 5.97 | learning rate: 4.109E-04 | global batch size: 512 | lm loss: 3.778691E+00 | loss scale: 16384.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.724 | TFLOPs: 64.75 | +[default7]: iteration 1406/ 3814 | consumed samples: 719872 | consumed tokens: 1474297856 | elapsed time per iteration (s): 5.94 | learning rate: 4.107E-04 | global batch size: 512 | lm loss: 3.801390E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.187 | TFLOPs: 65.10 | +[default7]: iteration 1407/ 3814 | consumed samples: 720384 | consumed tokens: 1475346432 | elapsed time per iteration (s): 6.03 | learning rate: 4.105E-04 | global batch size: 512 | lm loss: 3.777219E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.852 | TFLOPs: 64.09 | +[default7]: iteration 1408/ 3814 | consumed samples: 720896 | consumed tokens: 1476395008 | elapsed time per iteration (s): 5.94 | learning rate: 4.103E-04 | global batch size: 512 | lm loss: 3.812572E+00 | loss scale: 16384.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.141 | TFLOPs: 65.06 | +[default7]: iteration 1409/ 3814 | consumed samples: 721408 | consumed tokens: 1477443584 | elapsed time per iteration (s): 6.00 | learning rate: 4.101E-04 | global batch size: 512 | lm loss: 3.777137E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.399 | TFLOPs: 64.50 | +[default7]: iteration 1410/ 3814 | consumed samples: 721920 | consumed tokens: 1478492160 | elapsed time per iteration (s): 5.92 | learning rate: 4.099E-04 | global batch size: 512 | lm loss: 3.771376E+00 | loss scale: 16384.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.508 | TFLOPs: 65.34 | +[default7]: iteration 1411/ 3814 | consumed samples: 722432 | consumed tokens: 1479540736 | elapsed time per iteration (s): 5.99 | learning rate: 4.097E-04 | global batch size: 512 | lm loss: 3.795939E+00 | loss scale: 16384.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.526 | TFLOPs: 64.60 | +[default7]: iteration 1412/ 3814 | consumed samples: 722944 | consumed tokens: 1480589312 | elapsed time per iteration (s): 6.01 | learning rate: 4.095E-04 | global batch size: 512 | lm loss: 3.787966E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.208 | TFLOPs: 64.36 | +[default7]: iteration 1413/ 3814 | consumed samples: 723456 | consumed tokens: 1481637888 | elapsed time per iteration (s): 5.81 | learning rate: 4.093E-04 | global batch size: 512 | lm loss: 3.796022E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.161 | TFLOPs: 66.59 | +[default7]: iteration 1414/ 3814 | consumed samples: 723968 | consumed tokens: 1482686464 | elapsed time per iteration (s): 5.99 | learning rate: 4.091E-04 | global batch size: 512 | lm loss: 3.792055E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.415 | TFLOPs: 64.51 | +[default7]: iteration 1415/ 3814 | consumed samples: 724480 | consumed tokens: 1483735040 | elapsed time per iteration (s): 5.99 | learning rate: 4.089E-04 | global batch size: 512 | lm loss: 3.779315E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.493 | TFLOPs: 64.57 | +[default7]: iteration 1416/ 3814 | consumed samples: 724992 | consumed tokens: 1484783616 | elapsed time per iteration (s): 6.02 | learning rate: 4.087E-04 | global batch size: 512 | lm loss: 3.767917E+00 | loss scale: 16384.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.044 | TFLOPs: 64.23 | +[default7]: iteration 1417/ 3814 | consumed samples: 725504 | consumed tokens: 1485832192 | elapsed time per iteration (s): 5.96 | learning rate: 4.085E-04 | global batch size: 512 | lm loss: 3.792643E+00 | loss scale: 16384.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.868 | TFLOPs: 64.86 | +[default7]: iteration 1418/ 3814 | consumed samples: 726016 | consumed tokens: 1486880768 | elapsed time per iteration (s): 6.10 | learning rate: 4.083E-04 | global batch size: 512 | lm loss: 3.773369E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.889 | TFLOPs: 63.36 | +[default7]: iteration 1419/ 3814 | consumed samples: 726528 | consumed tokens: 1487929344 | elapsed time per iteration (s): 5.94 | learning rate: 4.082E-04 | global batch size: 512 | lm loss: 3.772822E+00 | loss scale: 16384.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.157 | TFLOPs: 65.08 | +[default7]: iteration 1420/ 3814 | consumed samples: 727040 | consumed tokens: 1488977920 | elapsed time per iteration (s): 5.98 | learning rate: 4.080E-04 | global batch size: 512 | lm loss: 3.795542E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.644 | TFLOPs: 64.69 | +[default7]: iteration 1421/ 3814 | consumed samples: 727552 | consumed tokens: 1490026496 | elapsed time per iteration (s): 6.02 | learning rate: 4.078E-04 | global batch size: 512 | lm loss: 3.783022E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.043 | TFLOPs: 64.23 | +[default7]: iteration 1422/ 3814 | consumed samples: 728064 | consumed tokens: 1491075072 | elapsed time per iteration (s): 5.99 | learning rate: 4.076E-04 | global batch size: 512 | lm loss: 3.773739E+00 | loss scale: 16384.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.514 | TFLOPs: 64.59 | +[default7]: iteration 1423/ 3814 | consumed samples: 728576 | consumed tokens: 1492123648 | elapsed time per iteration (s): 5.99 | learning rate: 4.074E-04 | global batch size: 512 | lm loss: 3.754287E+00 | loss scale: 16384.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.414 | TFLOPs: 64.51 | +[default7]: iteration 1424/ 3814 | consumed samples: 729088 | consumed tokens: 1493172224 | elapsed time per iteration (s): 5.94 | learning rate: 4.072E-04 | global batch size: 512 | lm loss: 3.760257E+00 | loss scale: 16384.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.181 | TFLOPs: 65.09 | +[default7]: iteration 1425/ 3814 | consumed samples: 729600 | consumed tokens: 1494220800 | elapsed time per iteration (s): 5.98 | learning rate: 4.070E-04 | global batch size: 512 | lm loss: 3.774572E+00 | loss scale: 16384.0 | grad norm: 0.206 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.638 | TFLOPs: 64.68 | +[default7]: iteration 1426/ 3814 | consumed samples: 730112 | consumed tokens: 1495269376 | elapsed time per iteration (s): 5.95 | learning rate: 4.068E-04 | global batch size: 512 | lm loss: 3.775158E+00 | loss scale: 16384.0 | grad norm: 0.189 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.011 | TFLOPs: 64.97 | +[default7]: iteration 1427/ 3814 | consumed samples: 730624 | consumed tokens: 1496317952 | elapsed time per iteration (s): 5.93 | learning rate: 4.066E-04 | global batch size: 512 | lm loss: 3.750719E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.390 | TFLOPs: 65.25 | +[default7]: iteration 1428/ 3814 | consumed samples: 731136 | consumed tokens: 1497366528 | elapsed time per iteration (s): 5.90 | learning rate: 4.064E-04 | global batch size: 512 | lm loss: 3.787150E+00 | loss scale: 16384.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.718 | TFLOPs: 65.50 | +[default7]: iteration 1429/ 3814 | consumed samples: 731648 | consumed tokens: 1498415104 | elapsed time per iteration (s): 5.98 | learning rate: 4.062E-04 | global batch size: 512 | lm loss: 3.771724E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.625 | TFLOPs: 64.67 | +[default7]: iteration 1430/ 3814 | consumed samples: 732160 | consumed tokens: 1499463680 | elapsed time per iteration (s): 5.97 | learning rate: 4.060E-04 | global batch size: 512 | lm loss: 3.761218E+00 | loss scale: 16384.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.717 | TFLOPs: 64.74 | +[default7]: iteration 1431/ 3814 | consumed samples: 732672 | consumed tokens: 1500512256 | elapsed time per iteration (s): 5.92 | learning rate: 4.058E-04 | global batch size: 512 | lm loss: 3.792743E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.520 | TFLOPs: 65.35 | +[default7]: iteration 1432/ 3814 | consumed samples: 733184 | consumed tokens: 1501560832 | elapsed time per iteration (s): 6.01 | learning rate: 4.056E-04 | global batch size: 512 | lm loss: 3.740414E+00 | loss scale: 16384.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.181 | TFLOPs: 64.34 | +[default7]: iteration 1433/ 3814 | consumed samples: 733696 | consumed tokens: 1502609408 | elapsed time per iteration (s): 6.09 | learning rate: 4.054E-04 | global batch size: 512 | lm loss: 3.769521E+00 | loss scale: 16384.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.080 | TFLOPs: 63.51 | +[default7]: iteration 1434/ 3814 | consumed samples: 734208 | consumed tokens: 1503657984 | elapsed time per iteration (s): 5.92 | learning rate: 4.052E-04 | global batch size: 512 | lm loss: 3.773015E+00 | loss scale: 16384.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.466 | TFLOPs: 65.31 | +[default7]: iteration 1435/ 3814 | consumed samples: 734720 | consumed tokens: 1504706560 | elapsed time per iteration (s): 5.91 | learning rate: 4.050E-04 | global batch size: 512 | lm loss: 3.811553E+00 | loss scale: 16384.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.644 | TFLOPs: 65.44 | +[default7]: iteration 1436/ 3814 | consumed samples: 735232 | consumed tokens: 1505755136 | elapsed time per iteration (s): 5.96 | learning rate: 4.048E-04 | global batch size: 512 | lm loss: 3.765778E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.885 | TFLOPs: 64.87 | +[default7]: iteration 1437/ 3814 | consumed samples: 735744 | consumed tokens: 1506803712 | elapsed time per iteration (s): 5.95 | learning rate: 4.046E-04 | global batch size: 512 | lm loss: 3.784581E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.983 | TFLOPs: 64.94 | +[default7]: iteration 1438/ 3814 | consumed samples: 736256 | consumed tokens: 1507852288 | elapsed time per iteration (s): 6.19 | learning rate: 4.044E-04 | global batch size: 512 | lm loss: 3.792374E+00 | loss scale: 16384.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.657 | TFLOPs: 62.43 | +[default7]: iteration 1439/ 3814 | consumed samples: 736768 | consumed tokens: 1508900864 | elapsed time per iteration (s): 6.12 | learning rate: 4.042E-04 | global batch size: 512 | lm loss: 3.760155E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.619 | TFLOPs: 63.16 | +[default7]: iteration 1440/ 3814 | consumed samples: 737280 | consumed tokens: 1509949440 | elapsed time per iteration (s): 6.16 | learning rate: 4.040E-04 | global batch size: 512 | lm loss: 3.759764E+00 | loss scale: 16384.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.169 | TFLOPs: 62.82 | +[default7]: iteration 1441/ 3814 | consumed samples: 737792 | consumed tokens: 1510998016 | elapsed time per iteration (s): 6.17 | learning rate: 4.039E-04 | global batch size: 512 | lm loss: 3.770216E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.945 | TFLOPs: 62.65 | +[default7]: iteration 1442/ 3814 | consumed samples: 738304 | consumed tokens: 1512046592 | elapsed time per iteration (s): 6.20 | learning rate: 4.037E-04 | global batch size: 512 | lm loss: 3.776569E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.628 | TFLOPs: 62.41 | +[default7]: iteration 1443/ 3814 | consumed samples: 738816 | consumed tokens: 1513095168 | elapsed time per iteration (s): 6.24 | learning rate: 4.035E-04 | global batch size: 512 | lm loss: 3.755628E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.005 | TFLOPs: 61.94 | +[default7]: iteration 1444/ 3814 | consumed samples: 739328 | consumed tokens: 1514143744 | elapsed time per iteration (s): 6.01 | learning rate: 4.033E-04 | global batch size: 512 | lm loss: 3.754983E+00 | loss scale: 16384.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.205 | TFLOPs: 64.36 | +[default7]: iteration 1445/ 3814 | consumed samples: 739840 | consumed tokens: 1515192320 | elapsed time per iteration (s): 6.23 | learning rate: 4.031E-04 | global batch size: 512 | lm loss: 3.766958E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.223 | TFLOPs: 62.10 | +[default7]: iteration 1446/ 3814 | consumed samples: 740352 | consumed tokens: 1516240896 | elapsed time per iteration (s): 6.11 | learning rate: 4.029E-04 | global batch size: 512 | lm loss: 3.768658E+00 | loss scale: 16384.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.807 | TFLOPs: 63.30 | +[default7]: iteration 1447/ 3814 | consumed samples: 740864 | consumed tokens: 1517289472 | elapsed time per iteration (s): 6.17 | learning rate: 4.027E-04 | global batch size: 512 | lm loss: 3.773230E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.016 | TFLOPs: 62.70 | +[default7]: iteration 1448/ 3814 | consumed samples: 741376 | consumed tokens: 1518338048 | elapsed time per iteration (s): 6.10 | learning rate: 4.025E-04 | global batch size: 512 | lm loss: 3.765839E+00 | loss scale: 16384.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.866 | TFLOPs: 63.34 | +[default7]: iteration 1449/ 3814 | consumed samples: 741888 | consumed tokens: 1519386624 | elapsed time per iteration (s): 6.00 | learning rate: 4.023E-04 | global batch size: 512 | lm loss: 3.769478E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.402 | TFLOPs: 64.50 | +[default7]: iteration 1450/ 3814 | consumed samples: 742400 | consumed tokens: 1520435200 | elapsed time per iteration (s): 6.07 | learning rate: 4.021E-04 | global batch size: 512 | lm loss: 3.755265E+00 | loss scale: 16384.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.411 | TFLOPs: 63.76 | +[default7]: iteration 1451/ 3814 | consumed samples: 742912 | consumed tokens: 1521483776 | elapsed time per iteration (s): 6.14 | learning rate: 4.019E-04 | global batch size: 512 | lm loss: 3.774984E+00 | loss scale: 16384.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.446 | TFLOPs: 63.03 | +[default7]: iteration 1452/ 3814 | consumed samples: 743424 | consumed tokens: 1522532352 | elapsed time per iteration (s): 6.03 | learning rate: 4.017E-04 | global batch size: 512 | lm loss: 3.745574E+00 | loss scale: 16384.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.961 | TFLOPs: 64.17 | +[default7]: iteration 1453/ 3814 | consumed samples: 743936 | consumed tokens: 1523580928 | elapsed time per iteration (s): 6.18 | learning rate: 4.015E-04 | global batch size: 512 | lm loss: 3.742274E+00 | loss scale: 16384.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.830 | TFLOPs: 62.56 | +[default7]: iteration 1454/ 3814 | consumed samples: 744448 | consumed tokens: 1524629504 | elapsed time per iteration (s): 6.25 | learning rate: 4.013E-04 | global batch size: 512 | lm loss: 3.812513E+00 | loss scale: 16384.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.867 | TFLOPs: 61.83 | +[default7]: iteration 1455/ 3814 | consumed samples: 744960 | consumed tokens: 1525678080 | elapsed time per iteration (s): 6.06 | learning rate: 4.011E-04 | global batch size: 512 | lm loss: 3.783341E+00 | loss scale: 16384.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.421 | TFLOPs: 63.76 | +[default7]: iteration 1456/ 3814 | consumed samples: 745472 | consumed tokens: 1526726656 | elapsed time per iteration (s): 6.24 | learning rate: 4.009E-04 | global batch size: 512 | lm loss: 3.747024E+00 | loss scale: 16384.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.031 | TFLOPs: 61.96 | +[default7]: iteration 1457/ 3814 | consumed samples: 745984 | consumed tokens: 1527775232 | elapsed time per iteration (s): 6.12 | learning rate: 4.007E-04 | global batch size: 512 | lm loss: 3.763813E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.660 | TFLOPs: 63.19 | +[default7]: iteration 1458/ 3814 | consumed samples: 746496 | consumed tokens: 1528823808 | elapsed time per iteration (s): 6.07 | learning rate: 4.005E-04 | global batch size: 512 | lm loss: 3.766269E+00 | loss scale: 16384.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.305 | TFLOPs: 63.68 | +[default7]: iteration 1459/ 3814 | consumed samples: 747008 | consumed tokens: 1529872384 | elapsed time per iteration (s): 6.15 | learning rate: 4.003E-04 | global batch size: 512 | lm loss: 3.770745E+00 | loss scale: 16384.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.269 | TFLOPs: 62.89 | +[default7]: iteration 1460/ 3814 | consumed samples: 747520 | consumed tokens: 1530920960 | elapsed time per iteration (s): 6.21 | learning rate: 4.001E-04 | global batch size: 512 | lm loss: 3.784802E+00 | loss scale: 16384.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.489 | TFLOPs: 62.30 | +[default7]: iteration 1461/ 3814 | consumed samples: 748032 | consumed tokens: 1531969536 | elapsed time per iteration (s): 6.08 | learning rate: 3.999E-04 | global batch size: 512 | lm loss: 3.741487E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.182 | TFLOPs: 63.58 | +[default7]: iteration 1462/ 3814 | consumed samples: 748544 | consumed tokens: 1533018112 | elapsed time per iteration (s): 6.00 | learning rate: 3.997E-04 | global batch size: 512 | lm loss: 3.744008E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.390 | TFLOPs: 64.50 | +[default7]: iteration 1463/ 3814 | consumed samples: 749056 | consumed tokens: 1534066688 | elapsed time per iteration (s): 6.05 | learning rate: 3.995E-04 | global batch size: 512 | lm loss: 3.742338E+00 | loss scale: 16384.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.692 | TFLOPs: 63.97 | +[default7]: iteration 1464/ 3814 | consumed samples: 749568 | consumed tokens: 1535115264 | elapsed time per iteration (s): 6.13 | learning rate: 3.993E-04 | global batch size: 512 | lm loss: 3.728380E+00 | loss scale: 16384.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.460 | TFLOPs: 63.04 | +[default7]: iteration 1465/ 3814 | consumed samples: 750080 | consumed tokens: 1536163840 | elapsed time per iteration (s): 6.25 | learning rate: 3.991E-04 | global batch size: 512 | lm loss: 3.739822E+00 | loss scale: 16384.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.864 | TFLOPs: 61.83 | +[default7]: iteration 1466/ 3814 | consumed samples: 750592 | consumed tokens: 1537212416 | elapsed time per iteration (s): 6.03 | learning rate: 3.989E-04 | global batch size: 512 | lm loss: 3.745776E+00 | loss scale: 16384.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.870 | TFLOPs: 64.10 | +[default7]: iteration 1467/ 3814 | consumed samples: 751104 | consumed tokens: 1538260992 | elapsed time per iteration (s): 6.05 | learning rate: 3.987E-04 | global batch size: 512 | lm loss: 3.730914E+00 | loss scale: 16384.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.572 | TFLOPs: 63.88 | +[default7]: iteration 1468/ 3814 | consumed samples: 751616 | consumed tokens: 1539309568 | elapsed time per iteration (s): 6.11 | learning rate: 3.985E-04 | global batch size: 512 | lm loss: 3.741377E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.810 | TFLOPs: 63.30 | +[default7]: iteration 1469/ 3814 | consumed samples: 752128 | consumed tokens: 1540358144 | elapsed time per iteration (s): 6.02 | learning rate: 3.983E-04 | global batch size: 512 | lm loss: 3.737052E+00 | loss scale: 16384.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.048 | TFLOPs: 64.24 | +[default7]: iteration 1470/ 3814 | consumed samples: 752640 | consumed tokens: 1541406720 | elapsed time per iteration (s): 6.03 | learning rate: 3.981E-04 | global batch size: 512 | lm loss: 3.777071E+00 | loss scale: 16384.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.921 | TFLOPs: 64.14 | +[default7]: iteration 1471/ 3814 | consumed samples: 753152 | consumed tokens: 1542455296 | elapsed time per iteration (s): 5.97 | learning rate: 3.979E-04 | global batch size: 512 | lm loss: 3.740764E+00 | loss scale: 16384.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.775 | TFLOPs: 64.79 | +[default7]: iteration 1472/ 3814 | consumed samples: 753664 | consumed tokens: 1543503872 | elapsed time per iteration (s): 6.01 | learning rate: 3.977E-04 | global batch size: 512 | lm loss: 3.732887E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.131 | TFLOPs: 64.30 | +[default7]: iteration 1473/ 3814 | consumed samples: 754176 | consumed tokens: 1544552448 | elapsed time per iteration (s): 6.19 | learning rate: 3.975E-04 | global batch size: 512 | lm loss: 3.715364E+00 | loss scale: 16384.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.761 | TFLOPs: 62.51 | +[default7]: iteration 1474/ 3814 | consumed samples: 754688 | consumed tokens: 1545601024 | elapsed time per iteration (s): 6.21 | learning rate: 3.973E-04 | global batch size: 512 | lm loss: 3.747260E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.431 | TFLOPs: 62.26 | +[default7]: iteration 1475/ 3814 | consumed samples: 755200 | consumed tokens: 1546649600 | elapsed time per iteration (s): 6.06 | learning rate: 3.971E-04 | global batch size: 512 | lm loss: 3.753190E+00 | loss scale: 16384.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.509 | TFLOPs: 63.83 | +[default7]: iteration 1476/ 3814 | consumed samples: 755712 | consumed tokens: 1547698176 | elapsed time per iteration (s): 6.28 | learning rate: 3.969E-04 | global batch size: 512 | lm loss: 3.758759E+00 | loss scale: 16384.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.563 | TFLOPs: 61.61 | +[default7]: iteration 1477/ 3814 | consumed samples: 756224 | consumed tokens: 1548746752 | elapsed time per iteration (s): 6.23 | learning rate: 3.967E-04 | global batch size: 512 | lm loss: 3.769436E+00 | loss scale: 16384.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.194 | TFLOPs: 62.08 | +[default7]: iteration 1478/ 3814 | consumed samples: 756736 | consumed tokens: 1549795328 | elapsed time per iteration (s): 6.19 | learning rate: 3.965E-04 | global batch size: 512 | lm loss: 3.751981E+00 | loss scale: 16384.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.740 | TFLOPs: 62.49 | +[default7]: iteration 1479/ 3814 | consumed samples: 757248 | consumed tokens: 1550843904 | elapsed time per iteration (s): 6.07 | learning rate: 3.963E-04 | global batch size: 512 | lm loss: 3.746196E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.371 | TFLOPs: 63.73 | +[default7]: iteration 1480/ 3814 | consumed samples: 757760 | consumed tokens: 1551892480 | elapsed time per iteration (s): 6.09 | learning rate: 3.961E-04 | global batch size: 512 | lm loss: 3.773828E+00 | loss scale: 16384.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.021 | TFLOPs: 63.46 | +[default7]: iteration 1481/ 3814 | consumed samples: 758272 | consumed tokens: 1552941056 | elapsed time per iteration (s): 6.14 | learning rate: 3.959E-04 | global batch size: 512 | lm loss: 3.725645E+00 | loss scale: 16384.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.361 | TFLOPs: 62.96 | +[default7]: iteration 1482/ 3814 | consumed samples: 758784 | consumed tokens: 1553989632 | elapsed time per iteration (s): 6.15 | learning rate: 3.957E-04 | global batch size: 512 | lm loss: 3.731320E+00 | loss scale: 16384.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.284 | TFLOPs: 62.91 | +[default7]: iteration 1483/ 3814 | consumed samples: 759296 | consumed tokens: 1555038208 | elapsed time per iteration (s): 6.21 | learning rate: 3.955E-04 | global batch size: 512 | lm loss: 3.737593E+00 | loss scale: 16384.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.473 | TFLOPs: 62.29 | +[default7]: iteration 1484/ 3814 | consumed samples: 759808 | consumed tokens: 1556086784 | elapsed time per iteration (s): 6.15 | learning rate: 3.953E-04 | global batch size: 512 | lm loss: 3.741982E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.268 | TFLOPs: 62.89 | +[default7]: iteration 1485/ 3814 | consumed samples: 760320 | consumed tokens: 1557135360 | elapsed time per iteration (s): 6.00 | learning rate: 3.951E-04 | global batch size: 512 | lm loss: 3.762238E+00 | loss scale: 16384.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.298 | TFLOPs: 64.43 | +[default7]: iteration 1486/ 3814 | consumed samples: 760832 | consumed tokens: 1558183936 | elapsed time per iteration (s): 6.23 | learning rate: 3.949E-04 | global batch size: 512 | lm loss: 3.742732E+00 | loss scale: 16384.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.163 | TFLOPs: 62.06 | +[default7]: iteration 1487/ 3814 | consumed samples: 761344 | consumed tokens: 1559232512 | elapsed time per iteration (s): 6.23 | learning rate: 3.947E-04 | global batch size: 512 | lm loss: 3.730617E+00 | loss scale: 16384.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.239 | TFLOPs: 62.12 | +[default7]: iteration 1488/ 3814 | consumed samples: 761856 | consumed tokens: 1560281088 | elapsed time per iteration (s): 6.34 | learning rate: 3.945E-04 | global batch size: 512 | lm loss: 3.736020E+00 | loss scale: 16384.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 80.773 | TFLOPs: 61.01 | +[default7]: iteration 1489/ 3814 | consumed samples: 762368 | consumed tokens: 1561329664 | elapsed time per iteration (s): 6.03 | learning rate: 3.943E-04 | global batch size: 512 | lm loss: 3.738961E+00 | loss scale: 16384.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.949 | TFLOPs: 64.16 | +[default7]: iteration 1490/ 3814 | consumed samples: 762880 | consumed tokens: 1562378240 | elapsed time per iteration (s): 6.19 | learning rate: 3.941E-04 | global batch size: 512 | lm loss: 3.716649E+00 | loss scale: 16384.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.768 | TFLOPs: 62.52 | +[default7]: iteration 1491/ 3814 | consumed samples: 763392 | consumed tokens: 1563426816 | elapsed time per iteration (s): 6.17 | learning rate: 3.939E-04 | global batch size: 512 | lm loss: 3.740269E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.044 | TFLOPs: 62.72 | +[default7]: iteration 1492/ 3814 | consumed samples: 763904 | consumed tokens: 1564475392 | elapsed time per iteration (s): 6.17 | learning rate: 3.937E-04 | global batch size: 512 | lm loss: 3.734725E+00 | loss scale: 16384.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.024 | TFLOPs: 62.71 | +[default7]: iteration 1493/ 3814 | consumed samples: 764416 | consumed tokens: 1565523968 | elapsed time per iteration (s): 6.17 | learning rate: 3.935E-04 | global batch size: 512 | lm loss: 3.752300E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.948 | TFLOPs: 62.65 | +[default7]: iteration 1494/ 3814 | consumed samples: 764928 | consumed tokens: 1566572544 | elapsed time per iteration (s): 6.10 | learning rate: 3.933E-04 | global batch size: 512 | lm loss: 3.743588E+00 | loss scale: 16384.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.964 | TFLOPs: 63.42 | +[default7]: iteration 1495/ 3814 | consumed samples: 765440 | consumed tokens: 1567621120 | elapsed time per iteration (s): 6.05 | learning rate: 3.931E-04 | global batch size: 512 | lm loss: 3.736679E+00 | loss scale: 16384.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.645 | TFLOPs: 63.93 | +[default7]: iteration 1496/ 3814 | consumed samples: 765952 | consumed tokens: 1568669696 | elapsed time per iteration (s): 6.01 | learning rate: 3.929E-04 | global batch size: 512 | lm loss: 3.749910E+00 | loss scale: 16384.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.151 | TFLOPs: 64.32 | +[default7]: iteration 1497/ 3814 | consumed samples: 766464 | consumed tokens: 1569718272 | elapsed time per iteration (s): 6.17 | learning rate: 3.926E-04 | global batch size: 512 | lm loss: 3.770547E+00 | loss scale: 16384.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.010 | TFLOPs: 62.70 | +[default7]: iteration 1498/ 3814 | consumed samples: 766976 | consumed tokens: 1570766848 | elapsed time per iteration (s): 6.09 | learning rate: 3.924E-04 | global batch size: 512 | lm loss: 3.762228E+00 | loss scale: 16384.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.125 | TFLOPs: 63.54 | +[default7]: iteration 1499/ 3814 | consumed samples: 767488 | consumed tokens: 1571815424 | elapsed time per iteration (s): 6.15 | learning rate: 3.922E-04 | global batch size: 512 | lm loss: 3.729666E+00 | loss scale: 16384.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.221 | TFLOPs: 62.86 | +[default7]: iteration 1500/ 3814 | consumed samples: 768000 | consumed tokens: 1572864000 | elapsed time per iteration (s): 6.08 | learning rate: 3.920E-04 | global batch size: 512 | lm loss: 3.736409E+00 | loss scale: 32768.0 | grad norm: 0.083 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.267 | TFLOPs: 63.65 | +[default0]:saving checkpoint at iteration 1500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 10:02:44,764] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1500 is begin to save! +[default0]:[2023-02-16 10:02:44,768] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:44,768] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:44,917] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:44,918] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:44,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:44,924] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:44,987] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:44,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:44,988] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:44,988] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,062] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,063] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,068] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,121] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,122] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,179] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,127] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,184] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,233] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,234] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,289] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,289] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,240] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,240] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,297] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,353] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,354] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,413] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,413] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,405] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,460] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,461] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,470] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,471] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,517] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,517] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,572] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,573] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,529] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,529] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,583] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,584] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,627] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,627] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,682] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,683] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,739] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,740] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,749] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,750] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,808] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,809] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,799] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,856] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,857] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,868] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:45,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,923] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:45,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,917] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:45,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:45,976] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:45,980] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:45,981] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,092] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,093] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,040] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,040] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,098] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,099] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,147] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,148] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,152] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,153] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,210] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,202] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,202] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,262] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,267] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,325] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,321] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,322] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,379] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,383] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,383] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,435] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,500] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,440] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,441] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,497] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,498] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,558] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,552] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,607] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,614] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,614] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 10:02:46,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,721] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 10:02:46,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,785] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,785] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 10:02:46,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 10:02:46,787] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_00_model_states.pt +[default0]:[2023-02-16 10:02:46,787] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 10:02:46,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_00_model_states.pt. +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:02:46,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,780] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 10:02:46,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 10:02:46,782] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_01_model_states.pt +[default1]:[2023-02-16 10:02:46,782] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 10:02:46,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:02:46,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:02:47,354] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,355] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,332] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,333] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,333] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,326] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,341] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,342] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,380] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,352] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,352] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,403] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,357] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,376] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,376] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,376] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,414] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,414] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,414] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,407] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,380] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,378] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,378] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,378] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,453] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,453] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,385] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,385] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,385] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,447] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,447] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,447] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,428] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,377] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,377] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,377] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,406] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,406] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,452] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,452] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,431] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,428] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,428] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,428] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,476] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,476] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,476] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,474] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,474] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,474] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,479] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,479] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,419] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,469] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,469] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,469] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,451] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,451] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,499] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,499] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,499] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,456] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,456] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,456] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,452] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,452] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,453] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,453] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,449] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,454] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,514] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,514] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,540] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,540] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,510] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,510] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,510] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,537] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,530] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,551] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,551] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,581] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,582] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,557] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,559] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,559] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,567] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,568] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,577] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,577] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,577] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,584] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,628] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,628] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default1]:[2023-02-16 10:02:47,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,575] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,629] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,554] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,570] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,570] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,604] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,588] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,562] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default2]:[2023-02-16 10:02:47,564] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:02:47,564] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:02:47,564] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default3]:[2023-02-16 10:02:47,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:02:47,555] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:02:47,556] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,575] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,575] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default1]:[2023-02-16 10:02:47,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:02:47,607] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:02:47,607] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default5]:[2023-02-16 10:02:47,678] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:02:47,678] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:02:47,678] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]:[2023-02-16 10:02:47,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:02:47,604] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:02:47,605] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,610] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,610] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,610] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default4]:[2023-02-16 10:02:47,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:02:47,640] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:02:47,640] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,689] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,689] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default6]:[2023-02-16 10:02:47,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,687] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,687] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default0]: successfully saved checkpoint at iteration 1500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default6]:[2023-02-16 10:02:47,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:02:47,752] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:02:47,752] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:[2023-02-16 10:02:47,782] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:02:47,782] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1500/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:02:47,782] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1500 is ready now! +[default7]:time (ms) | save-checkpoint: 3018.99 +[default7]: iteration 1501/ 3814 | consumed samples: 768512 | consumed tokens: 1573912576 | elapsed time per iteration (s): 9.22 | learning rate: 3.918E-04 | global batch size: 512 | lm loss: 3.738948E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 55.544 | TFLOPs: 41.95 | +[default7]: iteration 1502/ 3814 | consumed samples: 769024 | consumed tokens: 1574961152 | elapsed time per iteration (s): 6.20 | learning rate: 3.916E-04 | global batch size: 512 | lm loss: 3.762254E+00 | loss scale: 32768.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.555 | TFLOPs: 62.35 | +[default7]: iteration 1503/ 3814 | consumed samples: 769536 | consumed tokens: 1576009728 | elapsed time per iteration (s): 6.15 | learning rate: 3.914E-04 | global batch size: 512 | lm loss: 3.748842E+00 | loss scale: 32768.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.296 | TFLOPs: 62.91 | +[default7]: iteration 1504/ 3814 | consumed samples: 770048 | consumed tokens: 1577058304 | elapsed time per iteration (s): 6.20 | learning rate: 3.912E-04 | global batch size: 512 | lm loss: 3.741363E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.610 | TFLOPs: 62.40 | +[default7]: iteration 1505/ 3814 | consumed samples: 770560 | consumed tokens: 1578106880 | elapsed time per iteration (s): 6.13 | learning rate: 3.910E-04 | global batch size: 512 | lm loss: 3.756463E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.535 | TFLOPs: 63.10 | +[default7]: iteration 1506/ 3814 | consumed samples: 771072 | consumed tokens: 1579155456 | elapsed time per iteration (s): 6.07 | learning rate: 3.908E-04 | global batch size: 512 | lm loss: 3.708803E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.308 | TFLOPs: 63.68 | +[default7]: iteration 1507/ 3814 | consumed samples: 771584 | consumed tokens: 1580204032 | elapsed time per iteration (s): 6.16 | learning rate: 3.906E-04 | global batch size: 512 | lm loss: 3.759132E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.158 | TFLOPs: 62.81 | +[default7]: iteration 1508/ 3814 | consumed samples: 772096 | consumed tokens: 1581252608 | elapsed time per iteration (s): 6.08 | learning rate: 3.904E-04 | global batch size: 512 | lm loss: 3.719534E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.198 | TFLOPs: 63.60 | +[default7]: iteration 1509/ 3814 | consumed samples: 772608 | consumed tokens: 1582301184 | elapsed time per iteration (s): 6.16 | learning rate: 3.902E-04 | global batch size: 512 | lm loss: 3.731996E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.180 | TFLOPs: 62.83 | +[default7]: iteration 1510/ 3814 | consumed samples: 773120 | consumed tokens: 1583349760 | elapsed time per iteration (s): 6.14 | learning rate: 3.900E-04 | global batch size: 512 | lm loss: 3.711596E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.358 | TFLOPs: 62.96 | +[default7]: iteration 1511/ 3814 | consumed samples: 773632 | consumed tokens: 1584398336 | elapsed time per iteration (s): 6.03 | learning rate: 3.898E-04 | global batch size: 512 | lm loss: 3.747220E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.920 | TFLOPs: 64.14 | +[default7]: iteration 1512/ 3814 | consumed samples: 774144 | consumed tokens: 1585446912 | elapsed time per iteration (s): 6.00 | learning rate: 3.896E-04 | global batch size: 512 | lm loss: 3.730829E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.364 | TFLOPs: 64.48 | +[default7]: iteration 1513/ 3814 | consumed samples: 774656 | consumed tokens: 1586495488 | elapsed time per iteration (s): 6.01 | learning rate: 3.894E-04 | global batch size: 512 | lm loss: 3.704251E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.211 | TFLOPs: 64.36 | +[default7]: iteration 1514/ 3814 | consumed samples: 775168 | consumed tokens: 1587544064 | elapsed time per iteration (s): 6.05 | learning rate: 3.892E-04 | global batch size: 512 | lm loss: 3.725115E+00 | loss scale: 32768.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.686 | TFLOPs: 63.96 | +[default7]: iteration 1515/ 3814 | consumed samples: 775680 | consumed tokens: 1588592640 | elapsed time per iteration (s): 6.06 | learning rate: 3.890E-04 | global batch size: 512 | lm loss: 3.692199E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.428 | TFLOPs: 63.77 | +[default7]: iteration 1516/ 3814 | consumed samples: 776192 | consumed tokens: 1589641216 | elapsed time per iteration (s): 5.97 | learning rate: 3.888E-04 | global batch size: 512 | lm loss: 3.723905E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.812 | TFLOPs: 64.81 | +[default7]: iteration 1517/ 3814 | consumed samples: 776704 | consumed tokens: 1590689792 | elapsed time per iteration (s): 6.05 | learning rate: 3.886E-04 | global batch size: 512 | lm loss: 3.698732E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.681 | TFLOPs: 63.96 | +[default7]: iteration 1518/ 3814 | consumed samples: 777216 | consumed tokens: 1591738368 | elapsed time per iteration (s): 6.06 | learning rate: 3.884E-04 | global batch size: 512 | lm loss: 3.727056E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.558 | TFLOPs: 63.87 | +[default7]: iteration 1519/ 3814 | consumed samples: 777728 | consumed tokens: 1592786944 | elapsed time per iteration (s): 6.03 | learning rate: 3.882E-04 | global batch size: 512 | lm loss: 3.727968E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.926 | TFLOPs: 64.15 | +[default7]: iteration 1520/ 3814 | consumed samples: 778240 | consumed tokens: 1593835520 | elapsed time per iteration (s): 5.98 | learning rate: 3.879E-04 | global batch size: 512 | lm loss: 3.711781E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.582 | TFLOPs: 64.64 | +[default7]: iteration 1521/ 3814 | consumed samples: 778752 | consumed tokens: 1594884096 | elapsed time per iteration (s): 5.99 | learning rate: 3.877E-04 | global batch size: 512 | lm loss: 3.735382E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.460 | TFLOPs: 64.55 | +[default7]: iteration 1522/ 3814 | consumed samples: 779264 | consumed tokens: 1595932672 | elapsed time per iteration (s): 5.99 | learning rate: 3.875E-04 | global batch size: 512 | lm loss: 3.718914E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.429 | TFLOPs: 64.53 | +[default7]: iteration 1523/ 3814 | consumed samples: 779776 | consumed tokens: 1596981248 | elapsed time per iteration (s): 6.02 | learning rate: 3.873E-04 | global batch size: 512 | lm loss: 3.705081E+00 | loss scale: 32768.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.077 | TFLOPs: 64.26 | +[default7]: iteration 1524/ 3814 | consumed samples: 780288 | consumed tokens: 1598029824 | elapsed time per iteration (s): 6.02 | learning rate: 3.871E-04 | global batch size: 512 | lm loss: 3.714145E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.084 | TFLOPs: 64.27 | +[default7]: iteration 1525/ 3814 | consumed samples: 780800 | consumed tokens: 1599078400 | elapsed time per iteration (s): 5.98 | learning rate: 3.869E-04 | global batch size: 512 | lm loss: 3.693273E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.568 | TFLOPs: 64.63 | +[default7]: iteration 1526/ 3814 | consumed samples: 781312 | consumed tokens: 1600126976 | elapsed time per iteration (s): 5.96 | learning rate: 3.867E-04 | global batch size: 512 | lm loss: 3.719347E+00 | loss scale: 32768.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.922 | TFLOPs: 64.90 | +[default7]: iteration 1527/ 3814 | consumed samples: 781824 | consumed tokens: 1601175552 | elapsed time per iteration (s): 5.98 | learning rate: 3.865E-04 | global batch size: 512 | lm loss: 3.718812E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.682 | TFLOPs: 64.72 | +[default7]: iteration 1528/ 3814 | consumed samples: 782336 | consumed tokens: 1602224128 | elapsed time per iteration (s): 5.94 | learning rate: 3.863E-04 | global batch size: 512 | lm loss: 3.695223E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.125 | TFLOPs: 65.05 | +[default7]: iteration 1529/ 3814 | consumed samples: 782848 | consumed tokens: 1603272704 | elapsed time per iteration (s): 6.01 | learning rate: 3.861E-04 | global batch size: 512 | lm loss: 3.710712E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.240 | TFLOPs: 64.38 | +[default7]: iteration 1530/ 3814 | consumed samples: 783360 | consumed tokens: 1604321280 | elapsed time per iteration (s): 5.74 | learning rate: 3.859E-04 | global batch size: 512 | lm loss: 3.710687E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.194 | TFLOPs: 67.37 | +[default7]: iteration 1531/ 3814 | consumed samples: 783872 | consumed tokens: 1605369856 | elapsed time per iteration (s): 6.07 | learning rate: 3.857E-04 | global batch size: 512 | lm loss: 3.696200E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.332 | TFLOPs: 63.70 | +[default7]: iteration 1532/ 3814 | consumed samples: 784384 | consumed tokens: 1606418432 | elapsed time per iteration (s): 5.95 | learning rate: 3.855E-04 | global batch size: 512 | lm loss: 3.680659E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.024 | TFLOPs: 64.98 | +[default7]: iteration 1533/ 3814 | consumed samples: 784896 | consumed tokens: 1607467008 | elapsed time per iteration (s): 6.05 | learning rate: 3.853E-04 | global batch size: 512 | lm loss: 3.710141E+00 | loss scale: 32768.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.579 | TFLOPs: 63.88 | +[default7]: iteration 1534/ 3814 | consumed samples: 785408 | consumed tokens: 1608515584 | elapsed time per iteration (s): 5.98 | learning rate: 3.851E-04 | global batch size: 512 | lm loss: 3.730395E+00 | loss scale: 32768.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.556 | TFLOPs: 64.62 | +[default7]: iteration 1535/ 3814 | consumed samples: 785920 | consumed tokens: 1609564160 | elapsed time per iteration (s): 5.96 | learning rate: 3.848E-04 | global batch size: 512 | lm loss: 3.724066E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.918 | TFLOPs: 64.89 | +[default7]: iteration 1536/ 3814 | consumed samples: 786432 | consumed tokens: 1610612736 | elapsed time per iteration (s): 5.94 | learning rate: 3.846E-04 | global batch size: 512 | lm loss: 3.728256E+00 | loss scale: 32768.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.135 | TFLOPs: 65.06 | +[default7]: iteration 1537/ 3814 | consumed samples: 786944 | consumed tokens: 1611661312 | elapsed time per iteration (s): 5.98 | learning rate: 3.844E-04 | global batch size: 512 | lm loss: 3.718967E+00 | loss scale: 32768.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.636 | TFLOPs: 64.68 | +[default7]: iteration 1538/ 3814 | consumed samples: 787456 | consumed tokens: 1612709888 | elapsed time per iteration (s): 6.05 | learning rate: 3.842E-04 | global batch size: 512 | lm loss: 3.703063E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.616 | TFLOPs: 63.91 | +[default7]: iteration 1539/ 3814 | consumed samples: 787968 | consumed tokens: 1613758464 | elapsed time per iteration (s): 6.00 | learning rate: 3.840E-04 | global batch size: 512 | lm loss: 3.707216E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.333 | TFLOPs: 64.45 | +[default7]: iteration 1540/ 3814 | consumed samples: 788480 | consumed tokens: 1614807040 | elapsed time per iteration (s): 5.92 | learning rate: 3.838E-04 | global batch size: 512 | lm loss: 3.719962E+00 | loss scale: 32768.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.522 | TFLOPs: 65.35 | +[default7]: iteration 1541/ 3814 | consumed samples: 788992 | consumed tokens: 1615855616 | elapsed time per iteration (s): 6.04 | learning rate: 3.836E-04 | global batch size: 512 | lm loss: 3.710266E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.805 | TFLOPs: 64.05 | +[default7]: iteration 1542/ 3814 | consumed samples: 789504 | consumed tokens: 1616904192 | elapsed time per iteration (s): 6.02 | learning rate: 3.834E-04 | global batch size: 512 | lm loss: 3.728158E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.040 | TFLOPs: 64.23 | +[default7]: iteration 1543/ 3814 | consumed samples: 790016 | consumed tokens: 1617952768 | elapsed time per iteration (s): 5.99 | learning rate: 3.832E-04 | global batch size: 512 | lm loss: 3.689325E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.534 | TFLOPs: 64.60 | +[default7]: iteration 1544/ 3814 | consumed samples: 790528 | consumed tokens: 1619001344 | elapsed time per iteration (s): 6.01 | learning rate: 3.830E-04 | global batch size: 512 | lm loss: 3.684962E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.193 | TFLOPs: 64.35 | +[default7]: iteration 1545/ 3814 | consumed samples: 791040 | consumed tokens: 1620049920 | elapsed time per iteration (s): 6.07 | learning rate: 3.828E-04 | global batch size: 512 | lm loss: 3.703469E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.394 | TFLOPs: 63.74 | +[default7]: iteration 1546/ 3814 | consumed samples: 791552 | consumed tokens: 1621098496 | elapsed time per iteration (s): 6.00 | learning rate: 3.826E-04 | global batch size: 512 | lm loss: 3.678368E+00 | loss scale: 32768.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.294 | TFLOPs: 64.42 | +[default7]: iteration 1547/ 3814 | consumed samples: 792064 | consumed tokens: 1622147072 | elapsed time per iteration (s): 5.99 | learning rate: 3.824E-04 | global batch size: 512 | lm loss: 3.676080E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.475 | TFLOPs: 64.56 | +[default7]: iteration 1548/ 3814 | consumed samples: 792576 | consumed tokens: 1623195648 | elapsed time per iteration (s): 6.16 | learning rate: 3.821E-04 | global batch size: 512 | lm loss: 3.678535E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.052 | TFLOPs: 62.73 | +[default7]: iteration 1549/ 3814 | consumed samples: 793088 | consumed tokens: 1624244224 | elapsed time per iteration (s): 6.15 | learning rate: 3.819E-04 | global batch size: 512 | lm loss: 3.703223E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.233 | TFLOPs: 62.87 | +[default7]: iteration 1550/ 3814 | consumed samples: 793600 | consumed tokens: 1625292800 | elapsed time per iteration (s): 6.16 | learning rate: 3.817E-04 | global batch size: 512 | lm loss: 3.706006E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.053 | TFLOPs: 62.73 | +[default7]: iteration 1551/ 3814 | consumed samples: 794112 | consumed tokens: 1626341376 | elapsed time per iteration (s): 6.23 | learning rate: 3.815E-04 | global batch size: 512 | lm loss: 3.684584E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.220 | TFLOPs: 62.10 | +[default7]: iteration 1552/ 3814 | consumed samples: 794624 | consumed tokens: 1627389952 | elapsed time per iteration (s): 6.01 | learning rate: 3.813E-04 | global batch size: 512 | lm loss: 3.701810E+00 | loss scale: 32768.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.160 | TFLOPs: 64.32 | +[default7]: iteration 1553/ 3814 | consumed samples: 795136 | consumed tokens: 1628438528 | elapsed time per iteration (s): 6.20 | learning rate: 3.811E-04 | global batch size: 512 | lm loss: 3.686327E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.601 | TFLOPs: 62.39 | +[default7]: iteration 1554/ 3814 | consumed samples: 795648 | consumed tokens: 1629487104 | elapsed time per iteration (s): 6.19 | learning rate: 3.809E-04 | global batch size: 512 | lm loss: 3.696540E+00 | loss scale: 32768.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.778 | TFLOPs: 62.52 | +[default7]: iteration 1555/ 3814 | consumed samples: 796160 | consumed tokens: 1630535680 | elapsed time per iteration (s): 6.27 | learning rate: 3.807E-04 | global batch size: 512 | lm loss: 3.667032E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.722 | TFLOPs: 61.73 | +[default7]: iteration 1556/ 3814 | consumed samples: 796672 | consumed tokens: 1631584256 | elapsed time per iteration (s): 6.07 | learning rate: 3.805E-04 | global batch size: 512 | lm loss: 3.712724E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.287 | TFLOPs: 63.66 | +[default7]: iteration 1557/ 3814 | consumed samples: 797184 | consumed tokens: 1632632832 | elapsed time per iteration (s): 6.08 | learning rate: 3.803E-04 | global batch size: 512 | lm loss: 3.691613E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.211 | TFLOPs: 63.61 | +[default7]: iteration 1558/ 3814 | consumed samples: 797696 | consumed tokens: 1633681408 | elapsed time per iteration (s): 6.19 | learning rate: 3.801E-04 | global batch size: 512 | lm loss: 3.674615E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.756 | TFLOPs: 62.51 | +[default7]: iteration 1559/ 3814 | consumed samples: 798208 | consumed tokens: 1634729984 | elapsed time per iteration (s): 6.26 | learning rate: 3.798E-04 | global batch size: 512 | lm loss: 3.688164E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.845 | TFLOPs: 61.82 | +[default7]: iteration 1560/ 3814 | consumed samples: 798720 | consumed tokens: 1635778560 | elapsed time per iteration (s): 6.01 | learning rate: 3.796E-04 | global batch size: 512 | lm loss: 3.711982E+00 | loss scale: 32768.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.223 | TFLOPs: 64.37 | +[default7]: iteration 1561/ 3814 | consumed samples: 799232 | consumed tokens: 1636827136 | elapsed time per iteration (s): 6.13 | learning rate: 3.794E-04 | global batch size: 512 | lm loss: 3.709213E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.555 | TFLOPs: 63.11 | +[default7]: iteration 1562/ 3814 | consumed samples: 799744 | consumed tokens: 1637875712 | elapsed time per iteration (s): 6.18 | learning rate: 3.792E-04 | global batch size: 512 | lm loss: 3.686139E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.891 | TFLOPs: 62.61 | +[default7]: iteration 1563/ 3814 | consumed samples: 800256 | consumed tokens: 1638924288 | elapsed time per iteration (s): 6.21 | learning rate: 3.790E-04 | global batch size: 512 | lm loss: 3.681002E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.410 | TFLOPs: 62.25 | +[default7]: iteration 1564/ 3814 | consumed samples: 800768 | consumed tokens: 1639972864 | elapsed time per iteration (s): 6.26 | learning rate: 3.788E-04 | global batch size: 512 | lm loss: 3.684984E+00 | loss scale: 32768.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.729 | TFLOPs: 61.73 | +[default7]: iteration 1565/ 3814 | consumed samples: 801280 | consumed tokens: 1641021440 | elapsed time per iteration (s): 6.11 | learning rate: 3.786E-04 | global batch size: 512 | lm loss: 3.708353E+00 | loss scale: 32768.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.781 | TFLOPs: 63.28 | +[default7]: iteration 1566/ 3814 | consumed samples: 801792 | consumed tokens: 1642070016 | elapsed time per iteration (s): 5.93 | learning rate: 3.784E-04 | global batch size: 512 | lm loss: 3.698162E+00 | loss scale: 32768.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.349 | TFLOPs: 65.22 | +[default7]: iteration 1567/ 3814 | consumed samples: 802304 | consumed tokens: 1643118592 | elapsed time per iteration (s): 5.99 | learning rate: 3.782E-04 | global batch size: 512 | lm loss: 3.699358E+00 | loss scale: 32768.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.416 | TFLOPs: 64.52 | +[default7]: iteration 1568/ 3814 | consumed samples: 802816 | consumed tokens: 1644167168 | elapsed time per iteration (s): 6.03 | learning rate: 3.780E-04 | global batch size: 512 | lm loss: 3.673452E+00 | loss scale: 32768.0 | grad norm: 0.099 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.866 | TFLOPs: 64.10 | +[default7]: iteration 1569/ 3814 | consumed samples: 803328 | consumed tokens: 1645215744 | elapsed time per iteration (s): 5.97 | learning rate: 3.777E-04 | global batch size: 512 | lm loss: 3.664589E+00 | loss scale: 32768.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.757 | TFLOPs: 64.77 | +[default7]: iteration 1570/ 3814 | consumed samples: 803840 | consumed tokens: 1646264320 | elapsed time per iteration (s): 6.01 | learning rate: 3.775E-04 | global batch size: 512 | lm loss: 3.698668E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.206 | TFLOPs: 64.36 | +[default7]: iteration 1571/ 3814 | consumed samples: 804352 | consumed tokens: 1647312896 | elapsed time per iteration (s): 5.94 | learning rate: 3.773E-04 | global batch size: 512 | lm loss: 3.670583E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.149 | TFLOPs: 65.07 | +[default7]: iteration 1572/ 3814 | consumed samples: 804864 | consumed tokens: 1648361472 | elapsed time per iteration (s): 6.03 | learning rate: 3.771E-04 | global batch size: 512 | lm loss: 3.691389E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.903 | TFLOPs: 64.13 | +[default7]: iteration 1573/ 3814 | consumed samples: 805376 | consumed tokens: 1649410048 | elapsed time per iteration (s): 5.99 | learning rate: 3.769E-04 | global batch size: 512 | lm loss: 3.691750E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.513 | TFLOPs: 64.59 | +[default7]: iteration 1574/ 3814 | consumed samples: 805888 | consumed tokens: 1650458624 | elapsed time per iteration (s): 6.02 | learning rate: 3.767E-04 | global batch size: 512 | lm loss: 3.722576E+00 | loss scale: 32768.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.087 | TFLOPs: 64.27 | +[default7]: iteration 1575/ 3814 | consumed samples: 806400 | consumed tokens: 1651507200 | elapsed time per iteration (s): 5.97 | learning rate: 3.765E-04 | global batch size: 512 | lm loss: 3.709702E+00 | loss scale: 32768.0 | grad norm: 0.214 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.782 | TFLOPs: 64.79 | +[default7]: iteration 1576/ 3814 | consumed samples: 806912 | consumed tokens: 1652555776 | elapsed time per iteration (s): 6.02 | learning rate: 3.763E-04 | global batch size: 512 | lm loss: 3.697412E+00 | loss scale: 32768.0 | grad norm: 0.187 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.047 | TFLOPs: 64.24 | +[default7]: iteration 1577/ 3814 | consumed samples: 807424 | consumed tokens: 1653604352 | elapsed time per iteration (s): 6.01 | learning rate: 3.761E-04 | global batch size: 512 | lm loss: 3.688877E+00 | loss scale: 32768.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.258 | TFLOPs: 64.40 | +[default7]: iteration 1578/ 3814 | consumed samples: 807936 | consumed tokens: 1654652928 | elapsed time per iteration (s): 6.09 | learning rate: 3.758E-04 | global batch size: 512 | lm loss: 3.680711E+00 | loss scale: 32768.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.070 | TFLOPs: 63.50 | +[default7]: iteration 1579/ 3814 | consumed samples: 808448 | consumed tokens: 1655701504 | elapsed time per iteration (s): 5.98 | learning rate: 3.756E-04 | global batch size: 512 | lm loss: 3.667280E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.562 | TFLOPs: 64.63 | +[default7]: iteration 1580/ 3814 | consumed samples: 808960 | consumed tokens: 1656750080 | elapsed time per iteration (s): 6.01 | learning rate: 3.754E-04 | global batch size: 512 | lm loss: 3.696988E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.227 | TFLOPs: 64.37 | +[default7]: iteration 1581/ 3814 | consumed samples: 809472 | consumed tokens: 1657798656 | elapsed time per iteration (s): 6.01 | learning rate: 3.752E-04 | global batch size: 512 | lm loss: 3.694416E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.139 | TFLOPs: 64.31 | +[default7]: iteration 1582/ 3814 | consumed samples: 809984 | consumed tokens: 1658847232 | elapsed time per iteration (s): 6.00 | learning rate: 3.750E-04 | global batch size: 512 | lm loss: 3.700777E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.316 | TFLOPs: 64.44 | +[default7]: iteration 1583/ 3814 | consumed samples: 810496 | consumed tokens: 1659895808 | elapsed time per iteration (s): 5.99 | learning rate: 3.748E-04 | global batch size: 512 | lm loss: 3.665059E+00 | loss scale: 32768.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.433 | TFLOPs: 64.53 | +[default7]: iteration 1584/ 3814 | consumed samples: 811008 | consumed tokens: 1660944384 | elapsed time per iteration (s): 6.01 | learning rate: 3.746E-04 | global batch size: 512 | lm loss: 3.686144E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.262 | TFLOPs: 64.40 | +[default7]: iteration 1585/ 3814 | consumed samples: 811520 | consumed tokens: 1661992960 | elapsed time per iteration (s): 5.96 | learning rate: 3.744E-04 | global batch size: 512 | lm loss: 3.687273E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.965 | TFLOPs: 64.93 | +[default7]: iteration 1586/ 3814 | consumed samples: 812032 | consumed tokens: 1663041536 | elapsed time per iteration (s): 6.01 | learning rate: 3.741E-04 | global batch size: 512 | lm loss: 3.645071E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.203 | TFLOPs: 64.36 | +[default7]: iteration 1587/ 3814 | consumed samples: 812544 | consumed tokens: 1664090112 | elapsed time per iteration (s): 6.00 | learning rate: 3.739E-04 | global batch size: 512 | lm loss: 3.678977E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.352 | TFLOPs: 64.47 | +[default7]: iteration 1588/ 3814 | consumed samples: 813056 | consumed tokens: 1665138688 | elapsed time per iteration (s): 5.97 | learning rate: 3.737E-04 | global batch size: 512 | lm loss: 3.667521E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.802 | TFLOPs: 64.81 | +[default7]: iteration 1589/ 3814 | consumed samples: 813568 | consumed tokens: 1666187264 | elapsed time per iteration (s): 5.99 | learning rate: 3.735E-04 | global batch size: 512 | lm loss: 3.665487E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.493 | TFLOPs: 64.57 | +[default7]: iteration 1590/ 3814 | consumed samples: 814080 | consumed tokens: 1667235840 | elapsed time per iteration (s): 5.99 | learning rate: 3.733E-04 | global batch size: 512 | lm loss: 3.652089E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.453 | TFLOPs: 64.54 | +[default7]: iteration 1591/ 3814 | consumed samples: 814592 | consumed tokens: 1668284416 | elapsed time per iteration (s): 6.02 | learning rate: 3.731E-04 | global batch size: 512 | lm loss: 3.694489E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.066 | TFLOPs: 64.25 | +[default7]: iteration 1592/ 3814 | consumed samples: 815104 | consumed tokens: 1669332992 | elapsed time per iteration (s): 6.06 | learning rate: 3.729E-04 | global batch size: 512 | lm loss: 3.684189E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.473 | TFLOPs: 63.80 | +[default7]: iteration 1593/ 3814 | consumed samples: 815616 | consumed tokens: 1670381568 | elapsed time per iteration (s): 5.96 | learning rate: 3.727E-04 | global batch size: 512 | lm loss: 3.641104E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.943 | TFLOPs: 64.91 | +[default7]: iteration 1594/ 3814 | consumed samples: 816128 | consumed tokens: 1671430144 | elapsed time per iteration (s): 6.02 | learning rate: 3.724E-04 | global batch size: 512 | lm loss: 3.646112E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.021 | TFLOPs: 64.22 | +[default7]: iteration 1595/ 3814 | consumed samples: 816640 | consumed tokens: 1672478720 | elapsed time per iteration (s): 5.98 | learning rate: 3.722E-04 | global batch size: 512 | lm loss: 3.689921E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.559 | TFLOPs: 64.62 | +[default7]: iteration 1596/ 3814 | consumed samples: 817152 | consumed tokens: 1673527296 | elapsed time per iteration (s): 6.05 | learning rate: 3.720E-04 | global batch size: 512 | lm loss: 3.680725E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.682 | TFLOPs: 63.96 | +[default7]: iteration 1597/ 3814 | consumed samples: 817664 | consumed tokens: 1674575872 | elapsed time per iteration (s): 5.95 | learning rate: 3.718E-04 | global batch size: 512 | lm loss: 3.673259E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.075 | TFLOPs: 65.01 | +[default7]: iteration 1598/ 3814 | consumed samples: 818176 | consumed tokens: 1675624448 | elapsed time per iteration (s): 5.91 | learning rate: 3.716E-04 | global batch size: 512 | lm loss: 3.703909E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.705 | TFLOPs: 65.49 | +[default7]: iteration 1599/ 3814 | consumed samples: 818688 | consumed tokens: 1676673024 | elapsed time per iteration (s): 5.99 | learning rate: 3.714E-04 | global batch size: 512 | lm loss: 3.670750E+00 | loss scale: 32768.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.436 | TFLOPs: 64.53 | +[default7]: iteration 1600/ 3814 | consumed samples: 819200 | consumed tokens: 1677721600 | elapsed time per iteration (s): 6.05 | learning rate: 3.712E-04 | global batch size: 512 | lm loss: 3.693774E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.653 | TFLOPs: 63.94 | +[default7]: iteration 1601/ 3814 | consumed samples: 819712 | consumed tokens: 1678770176 | elapsed time per iteration (s): 6.00 | learning rate: 3.710E-04 | global batch size: 512 | lm loss: 3.642503E+00 | loss scale: 32768.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.290 | TFLOPs: 64.42 | +[default7]: iteration 1602/ 3814 | consumed samples: 820224 | consumed tokens: 1679818752 | elapsed time per iteration (s): 5.98 | learning rate: 3.707E-04 | global batch size: 512 | lm loss: 3.657582E+00 | loss scale: 32768.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.564 | TFLOPs: 64.63 | +[default7]: iteration 1603/ 3814 | consumed samples: 820736 | consumed tokens: 1680867328 | elapsed time per iteration (s): 5.97 | learning rate: 3.705E-04 | global batch size: 512 | lm loss: 3.689915E+00 | loss scale: 32768.0 | grad norm: 0.167 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.831 | TFLOPs: 64.83 | +[default7]: iteration 1604/ 3814 | consumed samples: 821248 | consumed tokens: 1681915904 | elapsed time per iteration (s): 6.00 | learning rate: 3.703E-04 | global batch size: 512 | lm loss: 3.657937E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.395 | TFLOPs: 64.50 | +[default7]: iteration 1605/ 3814 | consumed samples: 821760 | consumed tokens: 1682964480 | elapsed time per iteration (s): 5.98 | learning rate: 3.701E-04 | global batch size: 512 | lm loss: 3.668263E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.640 | TFLOPs: 64.68 | +[default7]: iteration 1606/ 3814 | consumed samples: 822272 | consumed tokens: 1684013056 | elapsed time per iteration (s): 6.00 | learning rate: 3.699E-04 | global batch size: 512 | lm loss: 3.681789E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.279 | TFLOPs: 64.41 | +[default7]: iteration 1607/ 3814 | consumed samples: 822784 | consumed tokens: 1685061632 | elapsed time per iteration (s): 5.99 | learning rate: 3.697E-04 | global batch size: 512 | lm loss: 3.702854E+00 | loss scale: 32768.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.538 | TFLOPs: 64.61 | +[default7]: iteration 1608/ 3814 | consumed samples: 823296 | consumed tokens: 1686110208 | elapsed time per iteration (s): 5.99 | learning rate: 3.695E-04 | global batch size: 512 | lm loss: 3.677997E+00 | loss scale: 32768.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.478 | TFLOPs: 64.56 | +[default7]: iteration 1609/ 3814 | consumed samples: 823808 | consumed tokens: 1687158784 | elapsed time per iteration (s): 6.18 | learning rate: 3.692E-04 | global batch size: 512 | lm loss: 3.664768E+00 | loss scale: 32768.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.865 | TFLOPs: 62.59 | +[default7]: iteration 1610/ 3814 | consumed samples: 824320 | consumed tokens: 1688207360 | elapsed time per iteration (s): 6.20 | learning rate: 3.690E-04 | global batch size: 512 | lm loss: 3.688694E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.609 | TFLOPs: 62.40 | +[default7]: iteration 1611/ 3814 | consumed samples: 824832 | consumed tokens: 1689255936 | elapsed time per iteration (s): 6.03 | learning rate: 3.688E-04 | global batch size: 512 | lm loss: 3.637403E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.852 | TFLOPs: 64.09 | +[default7]: iteration 1612/ 3814 | consumed samples: 825344 | consumed tokens: 1690304512 | elapsed time per iteration (s): 6.11 | learning rate: 3.686E-04 | global batch size: 512 | lm loss: 3.674909E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.826 | TFLOPs: 63.31 | +[default7]: iteration 1613/ 3814 | consumed samples: 825856 | consumed tokens: 1691353088 | elapsed time per iteration (s): 6.02 | learning rate: 3.684E-04 | global batch size: 512 | lm loss: 3.662309E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.992 | TFLOPs: 64.20 | +[default7]: iteration 1614/ 3814 | consumed samples: 826368 | consumed tokens: 1692401664 | elapsed time per iteration (s): 6.04 | learning rate: 3.682E-04 | global batch size: 512 | lm loss: 3.667384E+00 | loss scale: 32768.0 | grad norm: 0.183 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.770 | TFLOPs: 64.03 | +[default7]: iteration 1615/ 3814 | consumed samples: 826880 | consumed tokens: 1693450240 | elapsed time per iteration (s): 6.02 | learning rate: 3.680E-04 | global batch size: 512 | lm loss: 3.679974E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.043 | TFLOPs: 64.23 | +[default7]: iteration 1616/ 3814 | consumed samples: 827392 | consumed tokens: 1694498816 | elapsed time per iteration (s): 6.03 | learning rate: 3.677E-04 | global batch size: 512 | lm loss: 3.672237E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.969 | TFLOPs: 64.18 | +[default7]: iteration 1617/ 3814 | consumed samples: 827904 | consumed tokens: 1695547392 | elapsed time per iteration (s): 5.99 | learning rate: 3.675E-04 | global batch size: 512 | lm loss: 3.659037E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.546 | TFLOPs: 64.61 | +[default7]: iteration 1618/ 3814 | consumed samples: 828416 | consumed tokens: 1696595968 | elapsed time per iteration (s): 5.93 | learning rate: 3.673E-04 | global batch size: 512 | lm loss: 3.659962E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.272 | TFLOPs: 65.16 | +[default7]: iteration 1619/ 3814 | consumed samples: 828928 | consumed tokens: 1697644544 | elapsed time per iteration (s): 6.01 | learning rate: 3.671E-04 | global batch size: 512 | lm loss: 3.662143E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.262 | TFLOPs: 64.40 | +[default7]: iteration 1620/ 3814 | consumed samples: 829440 | consumed tokens: 1698693120 | elapsed time per iteration (s): 5.98 | learning rate: 3.669E-04 | global batch size: 512 | lm loss: 3.637828E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.685 | TFLOPs: 64.72 | +[default7]: iteration 1621/ 3814 | consumed samples: 829952 | consumed tokens: 1699741696 | elapsed time per iteration (s): 6.00 | learning rate: 3.667E-04 | global batch size: 512 | lm loss: 3.649821E+00 | loss scale: 32768.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.341 | TFLOPs: 64.46 | +[default7]: iteration 1622/ 3814 | consumed samples: 830464 | consumed tokens: 1700790272 | elapsed time per iteration (s): 5.99 | learning rate: 3.664E-04 | global batch size: 512 | lm loss: 3.652964E+00 | loss scale: 32768.0 | grad norm: 0.101 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.529 | TFLOPs: 64.60 | +[default7]: iteration 1623/ 3814 | consumed samples: 830976 | consumed tokens: 1701838848 | elapsed time per iteration (s): 6.02 | learning rate: 3.662E-04 | global batch size: 512 | lm loss: 3.660509E+00 | loss scale: 32768.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.095 | TFLOPs: 64.27 | +[default7]: iteration 1624/ 3814 | consumed samples: 831488 | consumed tokens: 1702887424 | elapsed time per iteration (s): 5.98 | learning rate: 3.660E-04 | global batch size: 512 | lm loss: 3.664114E+00 | loss scale: 32768.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.600 | TFLOPs: 64.65 | +[default7]: iteration 1625/ 3814 | consumed samples: 832000 | consumed tokens: 1703936000 | elapsed time per iteration (s): 5.98 | learning rate: 3.658E-04 | global batch size: 512 | lm loss: 3.617130E+00 | loss scale: 32768.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.675 | TFLOPs: 64.71 | +[default7]: iteration 1626/ 3814 | consumed samples: 832512 | consumed tokens: 1704984576 | elapsed time per iteration (s): 5.68 | learning rate: 3.656E-04 | global batch size: 512 | lm loss: 3.646620E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 90.204 | TFLOPs: 68.13 | +[default7]: iteration 1627/ 3814 | consumed samples: 833024 | consumed tokens: 1706033152 | elapsed time per iteration (s): 6.01 | learning rate: 3.654E-04 | global batch size: 512 | lm loss: 3.636951E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.193 | TFLOPs: 64.35 | +[default7]: iteration 1628/ 3814 | consumed samples: 833536 | consumed tokens: 1707081728 | elapsed time per iteration (s): 6.00 | learning rate: 3.652E-04 | global batch size: 512 | lm loss: 3.665863E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.311 | TFLOPs: 64.44 | +[default7]: iteration 1629/ 3814 | consumed samples: 834048 | consumed tokens: 1708130304 | elapsed time per iteration (s): 6.03 | learning rate: 3.649E-04 | global batch size: 512 | lm loss: 3.678046E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.908 | TFLOPs: 64.13 | +[default7]: iteration 1630/ 3814 | consumed samples: 834560 | consumed tokens: 1709178880 | elapsed time per iteration (s): 5.97 | learning rate: 3.647E-04 | global batch size: 512 | lm loss: 3.644925E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.736 | TFLOPs: 64.76 | +[default7]: iteration 1631/ 3814 | consumed samples: 835072 | consumed tokens: 1710227456 | elapsed time per iteration (s): 6.04 | learning rate: 3.645E-04 | global batch size: 512 | lm loss: 3.662747E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.780 | TFLOPs: 64.04 | +[default7]: iteration 1632/ 3814 | consumed samples: 835584 | consumed tokens: 1711276032 | elapsed time per iteration (s): 5.97 | learning rate: 3.643E-04 | global batch size: 512 | lm loss: 3.652800E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.721 | TFLOPs: 64.75 | +[default7]: iteration 1633/ 3814 | consumed samples: 836096 | consumed tokens: 1712324608 | elapsed time per iteration (s): 5.99 | learning rate: 3.641E-04 | global batch size: 512 | lm loss: 3.616448E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.409 | TFLOPs: 64.51 | +[default7]: iteration 1634/ 3814 | consumed samples: 836608 | consumed tokens: 1713373184 | elapsed time per iteration (s): 5.97 | learning rate: 3.639E-04 | global batch size: 512 | lm loss: 3.617612E+00 | loss scale: 32768.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.818 | TFLOPs: 64.82 | +[default7]: iteration 1635/ 3814 | consumed samples: 837120 | consumed tokens: 1714421760 | elapsed time per iteration (s): 5.96 | learning rate: 3.636E-04 | global batch size: 512 | lm loss: 3.642684E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.874 | TFLOPs: 64.86 | +[default7]: iteration 1636/ 3814 | consumed samples: 837632 | consumed tokens: 1715470336 | elapsed time per iteration (s): 6.00 | learning rate: 3.634E-04 | global batch size: 512 | lm loss: 3.650798E+00 | loss scale: 32768.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.308 | TFLOPs: 64.43 | +[default7]: iteration 1637/ 3814 | consumed samples: 838144 | consumed tokens: 1716518912 | elapsed time per iteration (s): 5.97 | learning rate: 3.632E-04 | global batch size: 512 | lm loss: 3.658388E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.702 | TFLOPs: 64.73 | +[default7]: iteration 1638/ 3814 | consumed samples: 838656 | consumed tokens: 1717567488 | elapsed time per iteration (s): 5.94 | learning rate: 3.630E-04 | global batch size: 512 | lm loss: 3.660428E+00 | loss scale: 32768.0 | grad norm: 0.170 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.237 | TFLOPs: 65.14 | +[default7]: iteration 1639/ 3814 | consumed samples: 839168 | consumed tokens: 1718616064 | elapsed time per iteration (s): 5.99 | learning rate: 3.628E-04 | global batch size: 512 | lm loss: 3.662735E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.483 | TFLOPs: 64.57 | +[default7]: iteration 1640/ 3814 | consumed samples: 839680 | consumed tokens: 1719664640 | elapsed time per iteration (s): 5.97 | learning rate: 3.626E-04 | global batch size: 512 | lm loss: 3.652236E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.758 | TFLOPs: 64.77 | +[default7]: iteration 1641/ 3814 | consumed samples: 840192 | consumed tokens: 1720713216 | elapsed time per iteration (s): 6.08 | learning rate: 3.623E-04 | global batch size: 512 | lm loss: 3.662029E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.273 | TFLOPs: 63.65 | +[default7]: iteration 1642/ 3814 | consumed samples: 840704 | consumed tokens: 1721761792 | elapsed time per iteration (s): 6.06 | learning rate: 3.621E-04 | global batch size: 512 | lm loss: 3.590040E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.556 | TFLOPs: 63.87 | +[default7]: iteration 1643/ 3814 | consumed samples: 841216 | consumed tokens: 1722810368 | elapsed time per iteration (s): 6.07 | learning rate: 3.619E-04 | global batch size: 512 | lm loss: 3.638072E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.315 | TFLOPs: 63.68 | +[default7]: iteration 1644/ 3814 | consumed samples: 841728 | consumed tokens: 1723858944 | elapsed time per iteration (s): 6.01 | learning rate: 3.617E-04 | global batch size: 512 | lm loss: 3.648710E+00 | loss scale: 32768.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.243 | TFLOPs: 64.38 | +[default7]: iteration 1645/ 3814 | consumed samples: 842240 | consumed tokens: 1724907520 | elapsed time per iteration (s): 6.04 | learning rate: 3.615E-04 | global batch size: 512 | lm loss: 3.625598E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.751 | TFLOPs: 64.01 | +[default7]: iteration 1646/ 3814 | consumed samples: 842752 | consumed tokens: 1725956096 | elapsed time per iteration (s): 6.03 | learning rate: 3.612E-04 | global batch size: 512 | lm loss: 3.647382E+00 | loss scale: 32768.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.933 | TFLOPs: 64.15 | +[default7]: iteration 1647/ 3814 | consumed samples: 843264 | consumed tokens: 1727004672 | elapsed time per iteration (s): 6.01 | learning rate: 3.610E-04 | global batch size: 512 | lm loss: 3.628199E+00 | loss scale: 32768.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.187 | TFLOPs: 64.34 | +[default7]: iteration 1648/ 3814 | consumed samples: 843776 | consumed tokens: 1728053248 | elapsed time per iteration (s): 6.00 | learning rate: 3.608E-04 | global batch size: 512 | lm loss: 3.615254E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.334 | TFLOPs: 64.45 | +[default7]: iteration 1649/ 3814 | consumed samples: 844288 | consumed tokens: 1729101824 | elapsed time per iteration (s): 5.93 | learning rate: 3.606E-04 | global batch size: 512 | lm loss: 3.665724E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.274 | TFLOPs: 65.16 | +[default7]: iteration 1650/ 3814 | consumed samples: 844800 | consumed tokens: 1730150400 | elapsed time per iteration (s): 6.17 | learning rate: 3.604E-04 | global batch size: 512 | lm loss: 3.627160E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.035 | TFLOPs: 62.72 | +[default7]: iteration 1651/ 3814 | consumed samples: 845312 | consumed tokens: 1731198976 | elapsed time per iteration (s): 5.98 | learning rate: 3.602E-04 | global batch size: 512 | lm loss: 3.637660E+00 | loss scale: 32768.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.563 | TFLOPs: 64.63 | +[default7]: iteration 1652/ 3814 | consumed samples: 845824 | consumed tokens: 1732247552 | elapsed time per iteration (s): 6.05 | learning rate: 3.599E-04 | global batch size: 512 | lm loss: 3.629122E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.659 | TFLOPs: 63.94 | +[default7]: iteration 1653/ 3814 | consumed samples: 846336 | consumed tokens: 1733296128 | elapsed time per iteration (s): 6.01 | learning rate: 3.597E-04 | global batch size: 512 | lm loss: 3.659568E+00 | loss scale: 32768.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.164 | TFLOPs: 64.33 | +[default7]: iteration 1654/ 3814 | consumed samples: 846848 | consumed tokens: 1734344704 | elapsed time per iteration (s): 6.02 | learning rate: 3.595E-04 | global batch size: 512 | lm loss: 3.624741E+00 | loss scale: 32768.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.984 | TFLOPs: 64.19 | +[default7]: iteration 1655/ 3814 | consumed samples: 847360 | consumed tokens: 1735393280 | elapsed time per iteration (s): 6.01 | learning rate: 3.593E-04 | global batch size: 512 | lm loss: 3.624833E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.147 | TFLOPs: 64.31 | +[default7]: iteration 1656/ 3814 | consumed samples: 847872 | consumed tokens: 1736441856 | elapsed time per iteration (s): 6.07 | learning rate: 3.591E-04 | global batch size: 512 | lm loss: 3.631857E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.410 | TFLOPs: 63.76 | +[default7]: iteration 1657/ 3814 | consumed samples: 848384 | consumed tokens: 1737490432 | elapsed time per iteration (s): 6.01 | learning rate: 3.588E-04 | global batch size: 512 | lm loss: 3.637281E+00 | loss scale: 32768.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.134 | TFLOPs: 64.30 | +[default7]: iteration 1658/ 3814 | consumed samples: 848896 | consumed tokens: 1738539008 | elapsed time per iteration (s): 5.99 | learning rate: 3.586E-04 | global batch size: 512 | lm loss: 3.654493E+00 | loss scale: 32768.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.460 | TFLOPs: 64.55 | +[default7]: iteration 1659/ 3814 | consumed samples: 849408 | consumed tokens: 1739587584 | elapsed time per iteration (s): 6.03 | learning rate: 3.584E-04 | global batch size: 512 | lm loss: 3.623875E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.973 | TFLOPs: 64.18 | +[default7]: iteration 1660/ 3814 | consumed samples: 849920 | consumed tokens: 1740636160 | elapsed time per iteration (s): 5.95 | learning rate: 3.582E-04 | global batch size: 512 | lm loss: 3.648441E+00 | loss scale: 32768.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.022 | TFLOPs: 64.97 | +[default7]: iteration 1661/ 3814 | consumed samples: 850432 | consumed tokens: 1741684736 | elapsed time per iteration (s): 6.00 | learning rate: 3.580E-04 | global batch size: 512 | lm loss: 3.661176E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.307 | TFLOPs: 64.43 | +[default7]: iteration 1662/ 3814 | consumed samples: 850944 | consumed tokens: 1742733312 | elapsed time per iteration (s): 5.99 | learning rate: 3.578E-04 | global batch size: 512 | lm loss: 3.631258E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.546 | TFLOPs: 64.61 | +[default7]: iteration 1663/ 3814 | consumed samples: 851456 | consumed tokens: 1743781888 | elapsed time per iteration (s): 6.03 | learning rate: 3.575E-04 | global batch size: 512 | lm loss: 3.649037E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.931 | TFLOPs: 64.15 | +[default7]: iteration 1664/ 3814 | consumed samples: 851968 | consumed tokens: 1744830464 | elapsed time per iteration (s): 5.95 | learning rate: 3.573E-04 | global batch size: 512 | lm loss: 3.624519E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.069 | TFLOPs: 65.01 | +[default7]: iteration 1665/ 3814 | consumed samples: 852480 | consumed tokens: 1745879040 | elapsed time per iteration (s): 6.01 | learning rate: 3.571E-04 | global batch size: 512 | lm loss: 3.642606E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.236 | TFLOPs: 64.38 | +[default7]: iteration 1666/ 3814 | consumed samples: 852992 | consumed tokens: 1746927616 | elapsed time per iteration (s): 5.97 | learning rate: 3.569E-04 | global batch size: 512 | lm loss: 3.627294E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.762 | TFLOPs: 64.78 | +[default7]: iteration 1667/ 3814 | consumed samples: 853504 | consumed tokens: 1747976192 | elapsed time per iteration (s): 6.01 | learning rate: 3.567E-04 | global batch size: 512 | lm loss: 3.635818E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.200 | TFLOPs: 64.35 | +[default7]: iteration 1668/ 3814 | consumed samples: 854016 | consumed tokens: 1749024768 | elapsed time per iteration (s): 6.00 | learning rate: 3.564E-04 | global batch size: 512 | lm loss: 3.582925E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.390 | TFLOPs: 64.50 | +[default7]: iteration 1669/ 3814 | consumed samples: 854528 | consumed tokens: 1750073344 | elapsed time per iteration (s): 6.04 | learning rate: 3.562E-04 | global batch size: 512 | lm loss: 3.641229E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.707 | TFLOPs: 63.98 | +[default7]: iteration 1670/ 3814 | consumed samples: 855040 | consumed tokens: 1751121920 | elapsed time per iteration (s): 5.99 | learning rate: 3.560E-04 | global batch size: 512 | lm loss: 3.646360E+00 | loss scale: 32768.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.420 | TFLOPs: 64.52 | +[default7]: iteration 1671/ 3814 | consumed samples: 855552 | consumed tokens: 1752170496 | elapsed time per iteration (s): 6.01 | learning rate: 3.558E-04 | global batch size: 512 | lm loss: 3.612888E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.177 | TFLOPs: 64.34 | +[default7]: iteration 1672/ 3814 | consumed samples: 856064 | consumed tokens: 1753219072 | elapsed time per iteration (s): 6.03 | learning rate: 3.556E-04 | global batch size: 512 | lm loss: 3.648034E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.869 | TFLOPs: 64.10 | +[default7]: iteration 1673/ 3814 | consumed samples: 856576 | consumed tokens: 1754267648 | elapsed time per iteration (s): 6.06 | learning rate: 3.553E-04 | global batch size: 512 | lm loss: 3.587703E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.420 | TFLOPs: 63.76 | +[default7]: iteration 1674/ 3814 | consumed samples: 857088 | consumed tokens: 1755316224 | elapsed time per iteration (s): 6.03 | learning rate: 3.551E-04 | global batch size: 512 | lm loss: 3.637150E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.881 | TFLOPs: 64.11 | +[default7]: iteration 1675/ 3814 | consumed samples: 857600 | consumed tokens: 1756364800 | elapsed time per iteration (s): 6.02 | learning rate: 3.549E-04 | global batch size: 512 | lm loss: 3.625204E+00 | loss scale: 32768.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.021 | TFLOPs: 64.22 | +[default7]: iteration 1676/ 3814 | consumed samples: 858112 | consumed tokens: 1757413376 | elapsed time per iteration (s): 5.97 | learning rate: 3.547E-04 | global batch size: 512 | lm loss: 3.602877E+00 | loss scale: 32768.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.742 | TFLOPs: 64.76 | +[default7]: iteration 1677/ 3814 | consumed samples: 858624 | consumed tokens: 1758461952 | elapsed time per iteration (s): 5.99 | learning rate: 3.545E-04 | global batch size: 512 | lm loss: 3.657733E+00 | loss scale: 32768.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.423 | TFLOPs: 64.52 | +[default7]: iteration 1678/ 3814 | consumed samples: 859136 | consumed tokens: 1759510528 | elapsed time per iteration (s): 6.13 | learning rate: 3.542E-04 | global batch size: 512 | lm loss: 3.626326E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.518 | TFLOPs: 63.08 | +[default7]: iteration 1679/ 3814 | consumed samples: 859648 | consumed tokens: 1760559104 | elapsed time per iteration (s): 5.96 | learning rate: 3.540E-04 | global batch size: 512 | lm loss: 3.649915E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.954 | TFLOPs: 64.92 | +[default7]: iteration 1680/ 3814 | consumed samples: 860160 | consumed tokens: 1761607680 | elapsed time per iteration (s): 5.96 | learning rate: 3.538E-04 | global batch size: 512 | lm loss: 3.600592E+00 | loss scale: 32768.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.844 | TFLOPs: 64.84 | +[default7]: iteration 1681/ 3814 | consumed samples: 860672 | consumed tokens: 1762656256 | elapsed time per iteration (s): 5.96 | learning rate: 3.536E-04 | global batch size: 512 | lm loss: 3.632447E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.836 | TFLOPs: 64.83 | +[default7]: iteration 1682/ 3814 | consumed samples: 861184 | consumed tokens: 1763704832 | elapsed time per iteration (s): 5.97 | learning rate: 3.534E-04 | global batch size: 512 | lm loss: 3.637537E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.718 | TFLOPs: 64.74 | +[default7]: iteration 1683/ 3814 | consumed samples: 861696 | consumed tokens: 1764753408 | elapsed time per iteration (s): 6.00 | learning rate: 3.531E-04 | global batch size: 512 | lm loss: 3.638644E+00 | loss scale: 32768.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.350 | TFLOPs: 64.47 | +[default7]: iteration 1684/ 3814 | consumed samples: 862208 | consumed tokens: 1765801984 | elapsed time per iteration (s): 5.73 | learning rate: 3.529E-04 | global batch size: 512 | lm loss: 3.615955E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.354 | TFLOPs: 67.49 | +[default7]: iteration 1685/ 3814 | consumed samples: 862720 | consumed tokens: 1766850560 | elapsed time per iteration (s): 6.03 | learning rate: 3.527E-04 | global batch size: 512 | lm loss: 3.649839E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.937 | TFLOPs: 64.15 | +[default7]: iteration 1686/ 3814 | consumed samples: 863232 | consumed tokens: 1767899136 | elapsed time per iteration (s): 5.92 | learning rate: 3.525E-04 | global batch size: 512 | lm loss: 3.623919E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.477 | TFLOPs: 65.32 | +[default7]: iteration 1687/ 3814 | consumed samples: 863744 | consumed tokens: 1768947712 | elapsed time per iteration (s): 6.02 | learning rate: 3.523E-04 | global batch size: 512 | lm loss: 3.635241E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.114 | TFLOPs: 64.29 | +[default7]: iteration 1688/ 3814 | consumed samples: 864256 | consumed tokens: 1769996288 | elapsed time per iteration (s): 6.06 | learning rate: 3.520E-04 | global batch size: 512 | lm loss: 3.610899E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.460 | TFLOPs: 63.79 | +[default7]: iteration 1689/ 3814 | consumed samples: 864768 | consumed tokens: 1771044864 | elapsed time per iteration (s): 6.03 | learning rate: 3.518E-04 | global batch size: 512 | lm loss: 3.605751E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.928 | TFLOPs: 64.15 | +[default7]: iteration 1690/ 3814 | consumed samples: 865280 | consumed tokens: 1772093440 | elapsed time per iteration (s): 6.01 | learning rate: 3.516E-04 | global batch size: 512 | lm loss: 3.628433E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.161 | TFLOPs: 64.32 | +[default7]: iteration 1691/ 3814 | consumed samples: 865792 | consumed tokens: 1773142016 | elapsed time per iteration (s): 6.00 | learning rate: 3.514E-04 | global batch size: 512 | lm loss: 3.611258E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.296 | TFLOPs: 64.42 | +[default7]: iteration 1692/ 3814 | consumed samples: 866304 | consumed tokens: 1774190592 | elapsed time per iteration (s): 5.98 | learning rate: 3.512E-04 | global batch size: 512 | lm loss: 3.647212E+00 | loss scale: 32768.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.599 | TFLOPs: 64.65 | +[default7]: iteration 1693/ 3814 | consumed samples: 866816 | consumed tokens: 1775239168 | elapsed time per iteration (s): 5.94 | learning rate: 3.509E-04 | global batch size: 512 | lm loss: 3.622571E+00 | loss scale: 32768.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.202 | TFLOPs: 65.11 | +[default7]: iteration 1694/ 3814 | consumed samples: 867328 | consumed tokens: 1776287744 | elapsed time per iteration (s): 6.07 | learning rate: 3.507E-04 | global batch size: 512 | lm loss: 3.630075E+00 | loss scale: 32768.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.347 | TFLOPs: 63.71 | +[default7]: iteration 1695/ 3814 | consumed samples: 867840 | consumed tokens: 1777336320 | elapsed time per iteration (s): 5.98 | learning rate: 3.505E-04 | global batch size: 512 | lm loss: 3.592321E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.550 | TFLOPs: 64.62 | +[default7]: iteration 1696/ 3814 | consumed samples: 868352 | consumed tokens: 1778384896 | elapsed time per iteration (s): 6.01 | learning rate: 3.503E-04 | global batch size: 512 | lm loss: 3.624621E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.138 | TFLOPs: 64.31 | +[default7]: iteration 1697/ 3814 | consumed samples: 868864 | consumed tokens: 1779433472 | elapsed time per iteration (s): 6.03 | learning rate: 3.500E-04 | global batch size: 512 | lm loss: 3.632061E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.874 | TFLOPs: 64.11 | +[default7]: iteration 1698/ 3814 | consumed samples: 869376 | consumed tokens: 1780482048 | elapsed time per iteration (s): 6.06 | learning rate: 3.498E-04 | global batch size: 512 | lm loss: 3.603837E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.491 | TFLOPs: 63.82 | +[default7]: iteration 1699/ 3814 | consumed samples: 869888 | consumed tokens: 1781530624 | elapsed time per iteration (s): 6.01 | learning rate: 3.496E-04 | global batch size: 512 | lm loss: 3.601886E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.201 | TFLOPs: 64.35 | +[default7]: iteration 1700/ 3814 | consumed samples: 870400 | consumed tokens: 1782579200 | elapsed time per iteration (s): 5.97 | learning rate: 3.494E-04 | global batch size: 512 | lm loss: 3.629231E+00 | loss scale: 32768.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.816 | TFLOPs: 64.82 | +[default7]: iteration 1701/ 3814 | consumed samples: 870912 | consumed tokens: 1783627776 | elapsed time per iteration (s): 5.94 | learning rate: 3.492E-04 | global batch size: 512 | lm loss: 3.615202E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.206 | TFLOPs: 65.11 | +[default7]: iteration 1702/ 3814 | consumed samples: 871424 | consumed tokens: 1784676352 | elapsed time per iteration (s): 6.03 | learning rate: 3.489E-04 | global batch size: 512 | lm loss: 3.639692E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.861 | TFLOPs: 64.10 | +[default7]: iteration 1703/ 3814 | consumed samples: 871936 | consumed tokens: 1785724928 | elapsed time per iteration (s): 5.94 | learning rate: 3.487E-04 | global batch size: 512 | lm loss: 3.612312E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.127 | TFLOPs: 65.05 | +[default7]: iteration 1704/ 3814 | consumed samples: 872448 | consumed tokens: 1786773504 | elapsed time per iteration (s): 6.00 | learning rate: 3.485E-04 | global batch size: 512 | lm loss: 3.614003E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.321 | TFLOPs: 64.44 | +[default7]: iteration 1705/ 3814 | consumed samples: 872960 | consumed tokens: 1787822080 | elapsed time per iteration (s): 5.97 | learning rate: 3.483E-04 | global batch size: 512 | lm loss: 3.597283E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.743 | TFLOPs: 64.76 | +[default7]: iteration 1706/ 3814 | consumed samples: 873472 | consumed tokens: 1788870656 | elapsed time per iteration (s): 5.99 | learning rate: 3.480E-04 | global batch size: 512 | lm loss: 3.633329E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.490 | TFLOPs: 64.57 | +[default7]: iteration 1707/ 3814 | consumed samples: 873984 | consumed tokens: 1789919232 | elapsed time per iteration (s): 5.99 | learning rate: 3.478E-04 | global batch size: 512 | lm loss: 3.608802E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.451 | TFLOPs: 64.54 | +[default7]: iteration 1708/ 3814 | consumed samples: 874496 | consumed tokens: 1790967808 | elapsed time per iteration (s): 5.99 | learning rate: 3.476E-04 | global batch size: 512 | lm loss: 3.613845E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.512 | TFLOPs: 64.59 | +[default7]: iteration 1709/ 3814 | consumed samples: 875008 | consumed tokens: 1792016384 | elapsed time per iteration (s): 6.07 | learning rate: 3.474E-04 | global batch size: 512 | lm loss: 3.620651E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.341 | TFLOPs: 63.70 | +[default7]: iteration 1710/ 3814 | consumed samples: 875520 | consumed tokens: 1793064960 | elapsed time per iteration (s): 5.98 | learning rate: 3.472E-04 | global batch size: 512 | lm loss: 3.608952E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.644 | TFLOPs: 64.69 | +[default7]: iteration 1711/ 3814 | consumed samples: 876032 | consumed tokens: 1794113536 | elapsed time per iteration (s): 5.97 | learning rate: 3.469E-04 | global batch size: 512 | lm loss: 3.620836E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.716 | TFLOPs: 64.74 | +[default7]: iteration 1712/ 3814 | consumed samples: 876544 | consumed tokens: 1795162112 | elapsed time per iteration (s): 6.02 | learning rate: 3.467E-04 | global batch size: 512 | lm loss: 3.597349E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.020 | TFLOPs: 64.22 | +[default7]: iteration 1713/ 3814 | consumed samples: 877056 | consumed tokens: 1796210688 | elapsed time per iteration (s): 6.06 | learning rate: 3.465E-04 | global batch size: 512 | lm loss: 3.603040E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.483 | TFLOPs: 63.81 | +[default7]: iteration 1714/ 3814 | consumed samples: 877568 | consumed tokens: 1797259264 | elapsed time per iteration (s): 6.03 | learning rate: 3.463E-04 | global batch size: 512 | lm loss: 3.616482E+00 | loss scale: 32768.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.890 | TFLOPs: 64.12 | +[default7]: iteration 1715/ 3814 | consumed samples: 878080 | consumed tokens: 1798307840 | elapsed time per iteration (s): 6.01 | learning rate: 3.460E-04 | global batch size: 512 | lm loss: 3.597972E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.208 | TFLOPs: 64.36 | +[default7]: iteration 1716/ 3814 | consumed samples: 878592 | consumed tokens: 1799356416 | elapsed time per iteration (s): 5.92 | learning rate: 3.458E-04 | global batch size: 512 | lm loss: 3.638299E+00 | loss scale: 32768.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.466 | TFLOPs: 65.31 | +[default7]: iteration 1717/ 3814 | consumed samples: 879104 | consumed tokens: 1800404992 | elapsed time per iteration (s): 5.98 | learning rate: 3.456E-04 | global batch size: 512 | lm loss: 3.606150E+00 | loss scale: 32768.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.598 | TFLOPs: 64.65 | +[default7]: iteration 1718/ 3814 | consumed samples: 879616 | consumed tokens: 1801453568 | elapsed time per iteration (s): 6.03 | learning rate: 3.454E-04 | global batch size: 512 | lm loss: 3.619472E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.852 | TFLOPs: 64.09 | +[default7]: iteration 1719/ 3814 | consumed samples: 880128 | consumed tokens: 1802502144 | elapsed time per iteration (s): 5.97 | learning rate: 3.452E-04 | global batch size: 512 | lm loss: 3.609216E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.750 | TFLOPs: 64.77 | +[default7]: iteration 1720/ 3814 | consumed samples: 880640 | consumed tokens: 1803550720 | elapsed time per iteration (s): 5.96 | learning rate: 3.449E-04 | global batch size: 512 | lm loss: 3.606606E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.932 | TFLOPs: 64.91 | +[default7]: iteration 1721/ 3814 | consumed samples: 881152 | consumed tokens: 1804599296 | elapsed time per iteration (s): 5.99 | learning rate: 3.447E-04 | global batch size: 512 | lm loss: 3.628738E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.518 | TFLOPs: 64.59 | +[default7]: iteration 1722/ 3814 | consumed samples: 881664 | consumed tokens: 1805647872 | elapsed time per iteration (s): 6.04 | learning rate: 3.445E-04 | global batch size: 512 | lm loss: 3.618087E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.762 | TFLOPs: 64.02 | +[default7]: iteration 1723/ 3814 | consumed samples: 882176 | consumed tokens: 1806696448 | elapsed time per iteration (s): 6.04 | learning rate: 3.443E-04 | global batch size: 512 | lm loss: 3.579570E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.785 | TFLOPs: 64.04 | +[default7]: iteration 1724/ 3814 | consumed samples: 882688 | consumed tokens: 1807745024 | elapsed time per iteration (s): 6.02 | learning rate: 3.440E-04 | global batch size: 512 | lm loss: 3.603476E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.113 | TFLOPs: 64.29 | +[default7]: iteration 1725/ 3814 | consumed samples: 883200 | consumed tokens: 1808793600 | elapsed time per iteration (s): 5.99 | learning rate: 3.438E-04 | global batch size: 512 | lm loss: 3.600475E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.481 | TFLOPs: 64.56 | +[default7]: iteration 1726/ 3814 | consumed samples: 883712 | consumed tokens: 1809842176 | elapsed time per iteration (s): 5.98 | learning rate: 3.436E-04 | global batch size: 512 | lm loss: 3.613236E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.676 | TFLOPs: 64.71 | +[default7]: iteration 1727/ 3814 | consumed samples: 884224 | consumed tokens: 1810890752 | elapsed time per iteration (s): 6.05 | learning rate: 3.434E-04 | global batch size: 512 | lm loss: 3.628526E+00 | loss scale: 32768.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.639 | TFLOPs: 63.93 | +[default7]: iteration 1728/ 3814 | consumed samples: 884736 | consumed tokens: 1811939328 | elapsed time per iteration (s): 5.92 | learning rate: 3.431E-04 | global batch size: 512 | lm loss: 3.598114E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.450 | TFLOPs: 65.30 | +[default7]: iteration 1729/ 3814 | consumed samples: 885248 | consumed tokens: 1812987904 | elapsed time per iteration (s): 5.89 | learning rate: 3.429E-04 | global batch size: 512 | lm loss: 3.642718E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.887 | TFLOPs: 65.63 | +[default7]: iteration 1730/ 3814 | consumed samples: 885760 | consumed tokens: 1814036480 | elapsed time per iteration (s): 5.90 | learning rate: 3.427E-04 | global batch size: 512 | lm loss: 3.603565E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.732 | TFLOPs: 65.51 | +[default7]: iteration 1731/ 3814 | consumed samples: 886272 | consumed tokens: 1815085056 | elapsed time per iteration (s): 5.96 | learning rate: 3.425E-04 | global batch size: 512 | lm loss: 3.592848E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.869 | TFLOPs: 64.86 | +[default7]: iteration 1732/ 3814 | consumed samples: 886784 | consumed tokens: 1816133632 | elapsed time per iteration (s): 6.00 | learning rate: 3.422E-04 | global batch size: 512 | lm loss: 3.621879E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.281 | TFLOPs: 64.41 | +[default7]: iteration 1733/ 3814 | consumed samples: 887296 | consumed tokens: 1817182208 | elapsed time per iteration (s): 6.00 | learning rate: 3.420E-04 | global batch size: 512 | lm loss: 3.580334E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.375 | TFLOPs: 64.48 | +[default7]: iteration 1734/ 3814 | consumed samples: 887808 | consumed tokens: 1818230784 | elapsed time per iteration (s): 5.99 | learning rate: 3.418E-04 | global batch size: 512 | lm loss: 3.605988E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.519 | TFLOPs: 64.59 | +[default7]: iteration 1735/ 3814 | consumed samples: 888320 | consumed tokens: 1819279360 | elapsed time per iteration (s): 6.02 | learning rate: 3.416E-04 | global batch size: 512 | lm loss: 3.607782E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.031 | TFLOPs: 64.23 | +[default7]: iteration 1736/ 3814 | consumed samples: 888832 | consumed tokens: 1820327936 | elapsed time per iteration (s): 5.99 | learning rate: 3.413E-04 | global batch size: 512 | lm loss: 3.602510E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.454 | TFLOPs: 64.54 | +[default7]: iteration 1737/ 3814 | consumed samples: 889344 | consumed tokens: 1821376512 | elapsed time per iteration (s): 6.00 | learning rate: 3.411E-04 | global batch size: 512 | lm loss: 3.617768E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.288 | TFLOPs: 64.42 | +[default7]: iteration 1738/ 3814 | consumed samples: 889856 | consumed tokens: 1822425088 | elapsed time per iteration (s): 6.00 | learning rate: 3.409E-04 | global batch size: 512 | lm loss: 3.604743E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.339 | TFLOPs: 64.46 | +[default7]: iteration 1739/ 3814 | consumed samples: 890368 | consumed tokens: 1823473664 | elapsed time per iteration (s): 6.04 | learning rate: 3.407E-04 | global batch size: 512 | lm loss: 3.594269E+00 | loss scale: 32768.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.797 | TFLOPs: 64.05 | +[default7]: iteration 1740/ 3814 | consumed samples: 890880 | consumed tokens: 1824522240 | elapsed time per iteration (s): 5.89 | learning rate: 3.404E-04 | global batch size: 512 | lm loss: 3.600340E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.884 | TFLOPs: 65.62 | +[default7]: iteration 1741/ 3814 | consumed samples: 891392 | consumed tokens: 1825570816 | elapsed time per iteration (s): 6.03 | learning rate: 3.402E-04 | global batch size: 512 | lm loss: 3.609021E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.896 | TFLOPs: 64.12 | +[default7]: iteration 1742/ 3814 | consumed samples: 891904 | consumed tokens: 1826619392 | elapsed time per iteration (s): 6.03 | learning rate: 3.400E-04 | global batch size: 512 | lm loss: 3.627056E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.873 | TFLOPs: 64.11 | +[default7]: iteration 1743/ 3814 | consumed samples: 892416 | consumed tokens: 1827667968 | elapsed time per iteration (s): 5.98 | learning rate: 3.398E-04 | global batch size: 512 | lm loss: 3.602957E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.558 | TFLOPs: 64.62 | +[default7]: iteration 1744/ 3814 | consumed samples: 892928 | consumed tokens: 1828716544 | elapsed time per iteration (s): 6.00 | learning rate: 3.395E-04 | global batch size: 512 | lm loss: 3.602857E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.386 | TFLOPs: 64.49 | +[default7]: iteration 1745/ 3814 | consumed samples: 893440 | consumed tokens: 1829765120 | elapsed time per iteration (s): 6.00 | learning rate: 3.393E-04 | global batch size: 512 | lm loss: 3.593844E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.306 | TFLOPs: 64.43 | +[default7]: iteration 1746/ 3814 | consumed samples: 893952 | consumed tokens: 1830813696 | elapsed time per iteration (s): 5.95 | learning rate: 3.391E-04 | global batch size: 512 | lm loss: 3.599033E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.057 | TFLOPs: 65.00 | +[default7]: iteration 1747/ 3814 | consumed samples: 894464 | consumed tokens: 1831862272 | elapsed time per iteration (s): 5.94 | learning rate: 3.389E-04 | global batch size: 512 | lm loss: 3.602907E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.257 | TFLOPs: 65.15 | +[default7]: iteration 1748/ 3814 | consumed samples: 894976 | consumed tokens: 1832910848 | elapsed time per iteration (s): 5.97 | learning rate: 3.386E-04 | global batch size: 512 | lm loss: 3.629151E+00 | loss scale: 32768.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.833 | TFLOPs: 64.83 | +[default7]: iteration 1749/ 3814 | consumed samples: 895488 | consumed tokens: 1833959424 | elapsed time per iteration (s): 5.97 | learning rate: 3.384E-04 | global batch size: 512 | lm loss: 3.580050E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.740 | TFLOPs: 64.76 | +[default7]: iteration 1750/ 3814 | consumed samples: 896000 | consumed tokens: 1835008000 | elapsed time per iteration (s): 5.98 | learning rate: 3.382E-04 | global batch size: 512 | lm loss: 3.572496E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.674 | TFLOPs: 64.71 | +[default0]:saving checkpoint at iteration 1750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 10:27:51,511] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step1750 is begin to save! +[default0]:[2023-02-16 10:27:51,515] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:51,515] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:51,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:51,663] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:51,671] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:51,671] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:51,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:51,727] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:51,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:51,719] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:51,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:51,779] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:51,784] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:51,784] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:51,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:51,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:51,887] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:51,887] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:51,839] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:51,839] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:51,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:51,895] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:51,948] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:51,948] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:51,952] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:51,953] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,007] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,008] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,001] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,002] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,061] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,064] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,065] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,124] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,125] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,115] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,116] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,171] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,171] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,187] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,226] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,226] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,254] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,323] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,324] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,292] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,292] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,362] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,446] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,508] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,508] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,545] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,545] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,563] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,564] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,620] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,597] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,598] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,653] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,676] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,732] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,708] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,709] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,794] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,795] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,827] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,828] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:52,885] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,886] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,851] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,852] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:52,911] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,911] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:52,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:52,946] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:52,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:52,974] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:53,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,033] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:53,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,001] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:53,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,059] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:53,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,091] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:53,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,117] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:53,183] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,183] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:53,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,158] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:53,216] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,216] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:53,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,240] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:53,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,274] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:53,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,297] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:53,352] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,353] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:53,338] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:53,405] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,406] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:53,418] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,419] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:53,479] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,479] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 10:27:53,462] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,462] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:53,525] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,526] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 10:27:53,538] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,538] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 10:27:53,539] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 10:27:53,540] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_01_model_states.pt +[default1]:[2023-02-16 10:27:53,540] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 10:27:53,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 10:27:53,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 10:27:53,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 10:27:53,583] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_00_model_states.pt +[default0]:[2023-02-16 10:27:53,583] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 10:27:53,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/mp_rank_00_model_states.pt. +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:27:53,735] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:27:54,253] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,253] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,253] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,279] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,280] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,265] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,265] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,265] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,325] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,274] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,274] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,274] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,275] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,276] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,276] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,318] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,318] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,318] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,329] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,329] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,329] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,313] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,313] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,313] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,373] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,373] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,373] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,331] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,331] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,368] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,368] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,368] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,356] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,356] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,334] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,335] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,388] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,388] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,324] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,325] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,325] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,391] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,391] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,391] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,419] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,419] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,419] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,420] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,420] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,420] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,336] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,336] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,342] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,342] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,342] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,427] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,427] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,403] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,445] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,446] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,446] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,380] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,380] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,410] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,410] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,410] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,393] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,393] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,393] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,457] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,442] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,442] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,442] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,421] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,421] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,399] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,399] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,399] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,437] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,437] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,437] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,449] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,505] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,506] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,530] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,530] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,530] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,487] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default3]:[2023-02-16 10:27:54,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:27:54,484] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:27:54,484] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default4]:[2023-02-16 10:27:54,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:27:54,468] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:27:54,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,465] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,465] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,465] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,553] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,553] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,553] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,574] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,574] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,574] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,505] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,571] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,571] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,598] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,560] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,560] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,536] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,536] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,537] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,588] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,588] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,625] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,615] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,615] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,615] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,601] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,605] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,604] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,604] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,604] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,624] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,624] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,624] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,662] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,662] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,662] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,588] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default5]:[2023-02-16 10:27:54,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:27:54,673] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:27:54,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]:[2023-02-16 10:27:54,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:27:54,639] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:27:54,639] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default2]:[2023-02-16 10:27:54,702] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:27:54,702] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:27:54,702] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default1]:[2023-02-16 10:27:54,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:27:54,666] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:27:54,666] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,693] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,719] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,719] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,719] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:[2023-02-16 10:27:54,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,774] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,774] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,787] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,787] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default6]:[2023-02-16 10:27:54,810] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:27:54,810] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:27:54,810] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default0]: successfully saved checkpoint at iteration 1750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:[2023-02-16 10:27:54,778] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:27:54,778] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step1750/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:27:54,778] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step1750 is ready now! +[default7]:time (ms) | save-checkpoint: 3309.33 +[default7]: iteration 1751/ 3814 | consumed samples: 896512 | consumed tokens: 1836056576 | elapsed time per iteration (s): 9.34 | learning rate: 3.380E-04 | global batch size: 512 | lm loss: 3.589311E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 54.820 | TFLOPs: 41.41 | +[default7]: iteration 1752/ 3814 | consumed samples: 897024 | consumed tokens: 1837105152 | elapsed time per iteration (s): 6.00 | learning rate: 3.377E-04 | global batch size: 512 | lm loss: 3.571896E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.365 | TFLOPs: 64.48 | +[default7]: iteration 1753/ 3814 | consumed samples: 897536 | consumed tokens: 1838153728 | elapsed time per iteration (s): 5.95 | learning rate: 3.375E-04 | global batch size: 512 | lm loss: 3.578456E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.981 | TFLOPs: 64.94 | +[default7]: iteration 1754/ 3814 | consumed samples: 898048 | consumed tokens: 1839202304 | elapsed time per iteration (s): 6.03 | learning rate: 3.373E-04 | global batch size: 512 | lm loss: 3.608243E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.867 | TFLOPs: 64.10 | +[default7]: iteration 1755/ 3814 | consumed samples: 898560 | consumed tokens: 1840250880 | elapsed time per iteration (s): 6.01 | learning rate: 3.371E-04 | global batch size: 512 | lm loss: 3.600196E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.253 | TFLOPs: 64.39 | +[default7]: iteration 1756/ 3814 | consumed samples: 899072 | consumed tokens: 1841299456 | elapsed time per iteration (s): 6.00 | learning rate: 3.368E-04 | global batch size: 512 | lm loss: 3.590771E+00 | loss scale: 32768.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.335 | TFLOPs: 64.45 | +[default7]: iteration 1757/ 3814 | consumed samples: 899584 | consumed tokens: 1842348032 | elapsed time per iteration (s): 6.00 | learning rate: 3.366E-04 | global batch size: 512 | lm loss: 3.608948E+00 | loss scale: 32768.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.377 | TFLOPs: 64.49 | +[default7]: iteration 1758/ 3814 | consumed samples: 900096 | consumed tokens: 1843396608 | elapsed time per iteration (s): 5.95 | learning rate: 3.364E-04 | global batch size: 512 | lm loss: 3.566149E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.011 | TFLOPs: 64.96 | +[default7]: iteration 1759/ 3814 | consumed samples: 900608 | consumed tokens: 1844445184 | elapsed time per iteration (s): 6.03 | learning rate: 3.362E-04 | global batch size: 512 | lm loss: 3.599035E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.940 | TFLOPs: 64.16 | +[default7]: iteration 1760/ 3814 | consumed samples: 901120 | consumed tokens: 1845493760 | elapsed time per iteration (s): 6.02 | learning rate: 3.359E-04 | global batch size: 512 | lm loss: 3.585518E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.061 | TFLOPs: 64.25 | +[default7]: iteration 1761/ 3814 | consumed samples: 901632 | consumed tokens: 1846542336 | elapsed time per iteration (s): 6.07 | learning rate: 3.357E-04 | global batch size: 512 | lm loss: 3.573401E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.300 | TFLOPs: 63.67 | +[default7]: iteration 1762/ 3814 | consumed samples: 902144 | consumed tokens: 1847590912 | elapsed time per iteration (s): 6.08 | learning rate: 3.355E-04 | global batch size: 512 | lm loss: 3.591962E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.146 | TFLOPs: 63.56 | +[default7]: iteration 1763/ 3814 | consumed samples: 902656 | consumed tokens: 1848639488 | elapsed time per iteration (s): 6.06 | learning rate: 3.353E-04 | global batch size: 512 | lm loss: 3.636163E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.506 | TFLOPs: 63.83 | +[default7]: iteration 1764/ 3814 | consumed samples: 903168 | consumed tokens: 1849688064 | elapsed time per iteration (s): 5.99 | learning rate: 3.350E-04 | global batch size: 512 | lm loss: 3.605259E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.425 | TFLOPs: 64.52 | +[default7]: iteration 1765/ 3814 | consumed samples: 903680 | consumed tokens: 1850736640 | elapsed time per iteration (s): 6.02 | learning rate: 3.348E-04 | global batch size: 512 | lm loss: 3.578619E+00 | loss scale: 32768.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.055 | TFLOPs: 64.24 | +[default7]: iteration 1766/ 3814 | consumed samples: 904192 | consumed tokens: 1851785216 | elapsed time per iteration (s): 5.96 | learning rate: 3.346E-04 | global batch size: 512 | lm loss: 3.561360E+00 | loss scale: 32768.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.893 | TFLOPs: 64.88 | +[default7]: iteration 1767/ 3814 | consumed samples: 904704 | consumed tokens: 1852833792 | elapsed time per iteration (s): 6.01 | learning rate: 3.344E-04 | global batch size: 512 | lm loss: 3.593002E+00 | loss scale: 32768.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.251 | TFLOPs: 64.39 | +[default7]: iteration 1768/ 3814 | consumed samples: 905216 | consumed tokens: 1853882368 | elapsed time per iteration (s): 6.01 | learning rate: 3.341E-04 | global batch size: 512 | lm loss: 3.618325E+00 | loss scale: 32768.0 | grad norm: 0.098 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.206 | TFLOPs: 64.36 | +[default7]: iteration 1769/ 3814 | consumed samples: 905728 | consumed tokens: 1854930944 | elapsed time per iteration (s): 6.01 | learning rate: 3.339E-04 | global batch size: 512 | lm loss: 3.612312E+00 | loss scale: 32768.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.153 | TFLOPs: 64.32 | +[default7]: iteration 1770/ 3814 | consumed samples: 906240 | consumed tokens: 1855979520 | elapsed time per iteration (s): 5.99 | learning rate: 3.337E-04 | global batch size: 512 | lm loss: 3.563844E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.523 | TFLOPs: 64.60 | +[default7]: iteration 1771/ 3814 | consumed samples: 906752 | consumed tokens: 1857028096 | elapsed time per iteration (s): 6.00 | learning rate: 3.335E-04 | global batch size: 512 | lm loss: 3.582871E+00 | loss scale: 32768.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.326 | TFLOPs: 64.45 | +[default7]: iteration 1772/ 3814 | consumed samples: 907264 | consumed tokens: 1858076672 | elapsed time per iteration (s): 5.98 | learning rate: 3.332E-04 | global batch size: 512 | lm loss: 3.595325E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.635 | TFLOPs: 64.68 | +[default7]: iteration 1773/ 3814 | consumed samples: 907776 | consumed tokens: 1859125248 | elapsed time per iteration (s): 6.04 | learning rate: 3.330E-04 | global batch size: 512 | lm loss: 3.585801E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.800 | TFLOPs: 64.05 | +[default7]: iteration 1774/ 3814 | consumed samples: 908288 | consumed tokens: 1860173824 | elapsed time per iteration (s): 5.99 | learning rate: 3.328E-04 | global batch size: 512 | lm loss: 3.557536E+00 | loss scale: 32768.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.485 | TFLOPs: 64.57 | +[default7]: iteration 1775/ 3814 | consumed samples: 908800 | consumed tokens: 1861222400 | elapsed time per iteration (s): 5.86 | learning rate: 3.325E-04 | global batch size: 512 | lm loss: 3.577457E+00 | loss scale: 32768.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.417 | TFLOPs: 66.03 | +[default7]: iteration 1776/ 3814 | consumed samples: 909312 | consumed tokens: 1862270976 | elapsed time per iteration (s): 6.03 | learning rate: 3.323E-04 | global batch size: 512 | lm loss: 3.571100E+00 | loss scale: 32768.0 | grad norm: 0.179 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.899 | TFLOPs: 64.12 | +[default7]: iteration 1777/ 3814 | consumed samples: 909824 | consumed tokens: 1863319552 | elapsed time per iteration (s): 6.04 | learning rate: 3.321E-04 | global batch size: 512 | lm loss: 3.589733E+00 | loss scale: 32768.0 | grad norm: 0.169 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.787 | TFLOPs: 64.04 | +[default7]: iteration 1778/ 3814 | consumed samples: 910336 | consumed tokens: 1864368128 | elapsed time per iteration (s): 5.97 | learning rate: 3.319E-04 | global batch size: 512 | lm loss: 3.596125E+00 | loss scale: 32768.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.776 | TFLOPs: 64.79 | +[default7]: iteration 1779/ 3814 | consumed samples: 910848 | consumed tokens: 1865416704 | elapsed time per iteration (s): 5.97 | learning rate: 3.316E-04 | global batch size: 512 | lm loss: 3.558930E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.739 | TFLOPs: 64.76 | +[default7]: iteration 1780/ 3814 | consumed samples: 911360 | consumed tokens: 1866465280 | elapsed time per iteration (s): 6.02 | learning rate: 3.314E-04 | global batch size: 512 | lm loss: 3.558844E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.008 | TFLOPs: 64.21 | +[default7]: iteration 1781/ 3814 | consumed samples: 911872 | consumed tokens: 1867513856 | elapsed time per iteration (s): 5.96 | learning rate: 3.312E-04 | global batch size: 512 | lm loss: 3.590488E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.938 | TFLOPs: 64.91 | +[default7]: iteration 1782/ 3814 | consumed samples: 912384 | consumed tokens: 1868562432 | elapsed time per iteration (s): 5.98 | learning rate: 3.310E-04 | global batch size: 512 | lm loss: 3.569530E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.599 | TFLOPs: 64.65 | +[default7]: iteration 1783/ 3814 | consumed samples: 912896 | consumed tokens: 1869611008 | elapsed time per iteration (s): 6.01 | learning rate: 3.307E-04 | global batch size: 512 | lm loss: 3.572531E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.249 | TFLOPs: 64.39 | +[default7]: iteration 1784/ 3814 | consumed samples: 913408 | consumed tokens: 1870659584 | elapsed time per iteration (s): 5.95 | learning rate: 3.305E-04 | global batch size: 512 | lm loss: 3.564052E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.092 | TFLOPs: 65.03 | +[default7]: iteration 1785/ 3814 | consumed samples: 913920 | consumed tokens: 1871708160 | elapsed time per iteration (s): 6.03 | learning rate: 3.303E-04 | global batch size: 512 | lm loss: 3.587100E+00 | loss scale: 32768.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.962 | TFLOPs: 64.17 | +[default7]: iteration 1786/ 3814 | consumed samples: 914432 | consumed tokens: 1872756736 | elapsed time per iteration (s): 6.00 | learning rate: 3.300E-04 | global batch size: 512 | lm loss: 3.586205E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.329 | TFLOPs: 64.45 | +[default7]: iteration 1787/ 3814 | consumed samples: 914944 | consumed tokens: 1873805312 | elapsed time per iteration (s): 5.98 | learning rate: 3.298E-04 | global batch size: 512 | lm loss: 3.569728E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.570 | TFLOPs: 64.63 | +[default7]: iteration 1788/ 3814 | consumed samples: 915456 | consumed tokens: 1874853888 | elapsed time per iteration (s): 5.99 | learning rate: 3.296E-04 | global batch size: 512 | lm loss: 3.567924E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.484 | TFLOPs: 64.57 | +[default7]: iteration 1789/ 3814 | consumed samples: 915968 | consumed tokens: 1875902464 | elapsed time per iteration (s): 5.91 | learning rate: 3.294E-04 | global batch size: 512 | lm loss: 3.575829E+00 | loss scale: 32768.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.609 | TFLOPs: 65.42 | +[default7]: iteration 1790/ 3814 | consumed samples: 916480 | consumed tokens: 1876951040 | elapsed time per iteration (s): 6.07 | learning rate: 3.291E-04 | global batch size: 512 | lm loss: 3.605640E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.340 | TFLOPs: 63.70 | +[default7]: iteration 1791/ 3814 | consumed samples: 916992 | consumed tokens: 1877999616 | elapsed time per iteration (s): 6.09 | learning rate: 3.289E-04 | global batch size: 512 | lm loss: 3.567613E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.100 | TFLOPs: 63.52 | +[default7]: iteration 1792/ 3814 | consumed samples: 917504 | consumed tokens: 1879048192 | elapsed time per iteration (s): 6.11 | learning rate: 3.287E-04 | global batch size: 512 | lm loss: 3.601574E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.859 | TFLOPs: 63.34 | +[default7]: iteration 1793/ 3814 | consumed samples: 918016 | consumed tokens: 1880096768 | elapsed time per iteration (s): 6.18 | learning rate: 3.284E-04 | global batch size: 512 | lm loss: 3.566249E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.827 | TFLOPs: 62.56 | +[default7]: iteration 1794/ 3814 | consumed samples: 918528 | consumed tokens: 1881145344 | elapsed time per iteration (s): 6.20 | learning rate: 3.282E-04 | global batch size: 512 | lm loss: 3.583418E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.626 | TFLOPs: 62.41 | +[default7]: iteration 1795/ 3814 | consumed samples: 919040 | consumed tokens: 1882193920 | elapsed time per iteration (s): 6.02 | learning rate: 3.280E-04 | global batch size: 512 | lm loss: 3.549464E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.044 | TFLOPs: 64.23 | +[default7]: iteration 1796/ 3814 | consumed samples: 919552 | consumed tokens: 1883242496 | elapsed time per iteration (s): 6.00 | learning rate: 3.278E-04 | global batch size: 512 | lm loss: 3.565054E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.396 | TFLOPs: 64.50 | +[default7]: iteration 1797/ 3814 | consumed samples: 920064 | consumed tokens: 1884291072 | elapsed time per iteration (s): 6.01 | learning rate: 3.275E-04 | global batch size: 512 | lm loss: 3.571921E+00 | loss scale: 32768.0 | grad norm: 0.159 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.156 | TFLOPs: 64.32 | +[default7]: iteration 1798/ 3814 | consumed samples: 920576 | consumed tokens: 1885339648 | elapsed time per iteration (s): 5.90 | learning rate: 3.273E-04 | global batch size: 512 | lm loss: 3.556427E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.804 | TFLOPs: 65.56 | +[default7]: iteration 1799/ 3814 | consumed samples: 921088 | consumed tokens: 1886388224 | elapsed time per iteration (s): 5.98 | learning rate: 3.271E-04 | global batch size: 512 | lm loss: 3.600621E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.661 | TFLOPs: 64.70 | +[default7]: iteration 1800/ 3814 | consumed samples: 921600 | consumed tokens: 1887436800 | elapsed time per iteration (s): 6.00 | learning rate: 3.269E-04 | global batch size: 512 | lm loss: 3.583172E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.371 | TFLOPs: 64.48 | +[default7]: iteration 1801/ 3814 | consumed samples: 922112 | consumed tokens: 1888485376 | elapsed time per iteration (s): 5.95 | learning rate: 3.266E-04 | global batch size: 512 | lm loss: 3.578407E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.041 | TFLOPs: 64.99 | +[default7]: iteration 1802/ 3814 | consumed samples: 922624 | consumed tokens: 1889533952 | elapsed time per iteration (s): 6.16 | learning rate: 3.264E-04 | global batch size: 512 | lm loss: 3.577965E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.182 | TFLOPs: 62.83 | +[default7]: iteration 1803/ 3814 | consumed samples: 923136 | consumed tokens: 1890582528 | elapsed time per iteration (s): 6.16 | learning rate: 3.262E-04 | global batch size: 512 | lm loss: 3.579065E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.118 | TFLOPs: 62.78 | +[default7]: iteration 1804/ 3814 | consumed samples: 923648 | consumed tokens: 1891631104 | elapsed time per iteration (s): 6.17 | learning rate: 3.259E-04 | global batch size: 512 | lm loss: 3.593261E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.008 | TFLOPs: 62.70 | +[default7]: iteration 1805/ 3814 | consumed samples: 924160 | consumed tokens: 1892679680 | elapsed time per iteration (s): 6.11 | learning rate: 3.257E-04 | global batch size: 512 | lm loss: 3.590553E+00 | loss scale: 32768.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.834 | TFLOPs: 63.32 | +[default7]: iteration 1806/ 3814 | consumed samples: 924672 | consumed tokens: 1893728256 | elapsed time per iteration (s): 6.16 | learning rate: 3.255E-04 | global batch size: 512 | lm loss: 3.570572E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.074 | TFLOPs: 62.75 | +[default7]: iteration 1807/ 3814 | consumed samples: 925184 | consumed tokens: 1894776832 | elapsed time per iteration (s): 5.98 | learning rate: 3.253E-04 | global batch size: 512 | lm loss: 3.562928E+00 | loss scale: 32768.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.560 | TFLOPs: 64.62 | +[default7]: iteration 1808/ 3814 | consumed samples: 925696 | consumed tokens: 1895825408 | elapsed time per iteration (s): 5.97 | learning rate: 3.250E-04 | global batch size: 512 | lm loss: 3.560436E+00 | loss scale: 32768.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.743 | TFLOPs: 64.76 | +[default7]: iteration 1809/ 3814 | consumed samples: 926208 | consumed tokens: 1896873984 | elapsed time per iteration (s): 5.93 | learning rate: 3.248E-04 | global batch size: 512 | lm loss: 3.586255E+00 | loss scale: 32768.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.353 | TFLOPs: 65.22 | +[default7]: iteration 1810/ 3814 | consumed samples: 926720 | consumed tokens: 1897922560 | elapsed time per iteration (s): 6.17 | learning rate: 3.246E-04 | global batch size: 512 | lm loss: 3.518225E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.920 | TFLOPs: 62.63 | +[default7]: iteration 1811/ 3814 | consumed samples: 927232 | consumed tokens: 1898971136 | elapsed time per iteration (s): 6.10 | learning rate: 3.243E-04 | global batch size: 512 | lm loss: 3.577366E+00 | loss scale: 32768.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.003 | TFLOPs: 63.45 | +[default7]: iteration 1812/ 3814 | consumed samples: 927744 | consumed tokens: 1900019712 | elapsed time per iteration (s): 6.15 | learning rate: 3.241E-04 | global batch size: 512 | lm loss: 3.582316E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.286 | TFLOPs: 62.91 | +[default7]: iteration 1813/ 3814 | consumed samples: 928256 | consumed tokens: 1901068288 | elapsed time per iteration (s): 6.14 | learning rate: 3.239E-04 | global batch size: 512 | lm loss: 3.555211E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.348 | TFLOPs: 62.95 | +[default7]: iteration 1814/ 3814 | consumed samples: 928768 | consumed tokens: 1902116864 | elapsed time per iteration (s): 6.14 | learning rate: 3.237E-04 | global batch size: 512 | lm loss: 3.543729E+00 | loss scale: 32768.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.403 | TFLOPs: 62.99 | +[default7]: iteration 1815/ 3814 | consumed samples: 929280 | consumed tokens: 1903165440 | elapsed time per iteration (s): 5.98 | learning rate: 3.234E-04 | global batch size: 512 | lm loss: 3.549226E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.580 | TFLOPs: 64.64 | +[default7]: iteration 1816/ 3814 | consumed samples: 929792 | consumed tokens: 1904214016 | elapsed time per iteration (s): 5.94 | learning rate: 3.232E-04 | global batch size: 512 | lm loss: 3.562646E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.264 | TFLOPs: 65.16 | +[default7]: iteration 1817/ 3814 | consumed samples: 930304 | consumed tokens: 1905262592 | elapsed time per iteration (s): 6.01 | learning rate: 3.230E-04 | global batch size: 512 | lm loss: 3.573412E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.176 | TFLOPs: 64.33 | +[default7]: iteration 1818/ 3814 | consumed samples: 930816 | consumed tokens: 1906311168 | elapsed time per iteration (s): 6.10 | learning rate: 3.227E-04 | global batch size: 512 | lm loss: 3.563536E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.871 | TFLOPs: 63.35 | +[default7]: iteration 1819/ 3814 | consumed samples: 931328 | consumed tokens: 1907359744 | elapsed time per iteration (s): 6.20 | learning rate: 3.225E-04 | global batch size: 512 | lm loss: 3.581551E+00 | loss scale: 32768.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.644 | TFLOPs: 62.42 | +[default7]: iteration 1820/ 3814 | consumed samples: 931840 | consumed tokens: 1908408320 | elapsed time per iteration (s): 6.21 | learning rate: 3.223E-04 | global batch size: 512 | lm loss: 3.549118E+00 | loss scale: 32768.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.432 | TFLOPs: 62.26 | +[default7]: iteration 1821/ 3814 | consumed samples: 932352 | consumed tokens: 1909456896 | elapsed time per iteration (s): 6.18 | learning rate: 3.220E-04 | global batch size: 512 | lm loss: 3.561394E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.913 | TFLOPs: 62.63 | +[default7]: iteration 1822/ 3814 | consumed samples: 932864 | consumed tokens: 1910505472 | elapsed time per iteration (s): 6.18 | learning rate: 3.218E-04 | global batch size: 512 | lm loss: 3.559779E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.912 | TFLOPs: 62.62 | +[default7]: iteration 1823/ 3814 | consumed samples: 933376 | consumed tokens: 1911554048 | elapsed time per iteration (s): 6.14 | learning rate: 3.216E-04 | global batch size: 512 | lm loss: 3.564111E+00 | loss scale: 32768.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.428 | TFLOPs: 63.01 | +[default7]: iteration 1824/ 3814 | consumed samples: 933888 | consumed tokens: 1912602624 | elapsed time per iteration (s): 6.18 | learning rate: 3.214E-04 | global batch size: 512 | lm loss: 3.547692E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.859 | TFLOPs: 62.58 | +[default7]: iteration 1825/ 3814 | consumed samples: 934400 | consumed tokens: 1913651200 | elapsed time per iteration (s): 6.16 | learning rate: 3.211E-04 | global batch size: 512 | lm loss: 3.546700E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.134 | TFLOPs: 62.79 | +[default7]: iteration 1826/ 3814 | consumed samples: 934912 | consumed tokens: 1914699776 | elapsed time per iteration (s): 6.15 | learning rate: 3.209E-04 | global batch size: 512 | lm loss: 3.559803E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.252 | TFLOPs: 62.88 | +[default7]: iteration 1827/ 3814 | consumed samples: 935424 | consumed tokens: 1915748352 | elapsed time per iteration (s): 5.98 | learning rate: 3.207E-04 | global batch size: 512 | lm loss: 3.573272E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.571 | TFLOPs: 64.63 | +[default7]: iteration 1828/ 3814 | consumed samples: 935936 | consumed tokens: 1916796928 | elapsed time per iteration (s): 6.20 | learning rate: 3.204E-04 | global batch size: 512 | lm loss: 3.567354E+00 | loss scale: 32768.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.619 | TFLOPs: 62.40 | +[default7]: iteration 1829/ 3814 | consumed samples: 936448 | consumed tokens: 1917845504 | elapsed time per iteration (s): 6.14 | learning rate: 3.202E-04 | global batch size: 512 | lm loss: 3.554120E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.347 | TFLOPs: 62.95 | +[default7]: iteration 1830/ 3814 | consumed samples: 936960 | consumed tokens: 1918894080 | elapsed time per iteration (s): 6.23 | learning rate: 3.200E-04 | global batch size: 512 | lm loss: 3.575736E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.124 | TFLOPs: 62.03 | +[default7]: iteration 1831/ 3814 | consumed samples: 937472 | consumed tokens: 1919942656 | elapsed time per iteration (s): 6.06 | learning rate: 3.197E-04 | global batch size: 512 | lm loss: 3.569541E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.497 | TFLOPs: 63.82 | +[default7]: iteration 1832/ 3814 | consumed samples: 937984 | consumed tokens: 1920991232 | elapsed time per iteration (s): 6.15 | learning rate: 3.195E-04 | global batch size: 512 | lm loss: 3.546381E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.230 | TFLOPs: 62.86 | +[default7]: iteration 1833/ 3814 | consumed samples: 938496 | consumed tokens: 1922039808 | elapsed time per iteration (s): 6.24 | learning rate: 3.193E-04 | global batch size: 512 | lm loss: 3.559599E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.101 | TFLOPs: 62.01 | +[default7]: iteration 1834/ 3814 | consumed samples: 939008 | consumed tokens: 1923088384 | elapsed time per iteration (s): 5.85 | learning rate: 3.191E-04 | global batch size: 512 | lm loss: 3.540066E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.501 | TFLOPs: 66.09 | +[default7]: iteration 1835/ 3814 | consumed samples: 939520 | consumed tokens: 1924136960 | elapsed time per iteration (s): 6.00 | learning rate: 3.188E-04 | global batch size: 512 | lm loss: 3.591409E+00 | loss scale: 32768.0 | grad norm: 0.160 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.367 | TFLOPs: 64.48 | +[default7]: iteration 1836/ 3814 | consumed samples: 940032 | consumed tokens: 1925185536 | elapsed time per iteration (s): 5.99 | learning rate: 3.186E-04 | global batch size: 512 | lm loss: 3.582816E+00 | loss scale: 32768.0 | grad norm: 0.155 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.407 | TFLOPs: 64.51 | +[default7]: iteration 1837/ 3814 | consumed samples: 940544 | consumed tokens: 1926234112 | elapsed time per iteration (s): 6.01 | learning rate: 3.184E-04 | global batch size: 512 | lm loss: 3.595688E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.140 | TFLOPs: 64.31 | +[default7]: iteration 1838/ 3814 | consumed samples: 941056 | consumed tokens: 1927282688 | elapsed time per iteration (s): 5.99 | learning rate: 3.181E-04 | global batch size: 512 | lm loss: 3.562698E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.473 | TFLOPs: 64.56 | +[default7]: iteration 1839/ 3814 | consumed samples: 941568 | consumed tokens: 1928331264 | elapsed time per iteration (s): 6.02 | learning rate: 3.179E-04 | global batch size: 512 | lm loss: 3.548602E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.092 | TFLOPs: 64.27 | +[default7]: iteration 1840/ 3814 | consumed samples: 942080 | consumed tokens: 1929379840 | elapsed time per iteration (s): 5.96 | learning rate: 3.177E-04 | global batch size: 512 | lm loss: 3.533677E+00 | loss scale: 32768.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.900 | TFLOPs: 64.88 | +[default7]: iteration 1841/ 3814 | consumed samples: 942592 | consumed tokens: 1930428416 | elapsed time per iteration (s): 6.03 | learning rate: 3.174E-04 | global batch size: 512 | lm loss: 3.540531E+00 | loss scale: 32768.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.894 | TFLOPs: 64.12 | +[default7]: iteration 1842/ 3814 | consumed samples: 943104 | consumed tokens: 1931476992 | elapsed time per iteration (s): 5.98 | learning rate: 3.172E-04 | global batch size: 512 | lm loss: 3.565282E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.635 | TFLOPs: 64.68 | +[default7]: iteration 1843/ 3814 | consumed samples: 943616 | consumed tokens: 1932525568 | elapsed time per iteration (s): 6.02 | learning rate: 3.170E-04 | global batch size: 512 | lm loss: 3.568366E+00 | loss scale: 32768.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.030 | TFLOPs: 64.22 | +[default7]: iteration 1844/ 3814 | consumed samples: 944128 | consumed tokens: 1933574144 | elapsed time per iteration (s): 5.97 | learning rate: 3.168E-04 | global batch size: 512 | lm loss: 3.566936E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.782 | TFLOPs: 64.79 | +[default7]: iteration 1845/ 3814 | consumed samples: 944640 | consumed tokens: 1934622720 | elapsed time per iteration (s): 6.00 | learning rate: 3.165E-04 | global batch size: 512 | lm loss: 3.537370E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.266 | TFLOPs: 64.40 | +[default7]: iteration 1846/ 3814 | consumed samples: 945152 | consumed tokens: 1935671296 | elapsed time per iteration (s): 6.00 | learning rate: 3.163E-04 | global batch size: 512 | lm loss: 3.527311E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.356 | TFLOPs: 64.47 | +[default7]: iteration 1847/ 3814 | consumed samples: 945664 | consumed tokens: 1936719872 | elapsed time per iteration (s): 5.98 | learning rate: 3.161E-04 | global batch size: 512 | lm loss: 3.580318E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.552 | TFLOPs: 64.62 | +[default7]: iteration 1848/ 3814 | consumed samples: 946176 | consumed tokens: 1937768448 | elapsed time per iteration (s): 5.89 | learning rate: 3.158E-04 | global batch size: 512 | lm loss: 3.552369E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.995 | TFLOPs: 65.71 | +[default7]: iteration 1849/ 3814 | consumed samples: 946688 | consumed tokens: 1938817024 | elapsed time per iteration (s): 5.98 | learning rate: 3.156E-04 | global batch size: 512 | lm loss: 3.573819E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.559 | TFLOPs: 64.62 | +[default7]: iteration 1850/ 3814 | consumed samples: 947200 | consumed tokens: 1939865600 | elapsed time per iteration (s): 6.05 | learning rate: 3.154E-04 | global batch size: 512 | lm loss: 3.525196E+00 | loss scale: 32768.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.659 | TFLOPs: 63.94 | +[default7]: iteration 1851/ 3814 | consumed samples: 947712 | consumed tokens: 1940914176 | elapsed time per iteration (s): 6.03 | learning rate: 3.151E-04 | global batch size: 512 | lm loss: 3.528255E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.856 | TFLOPs: 64.09 | +[default7]: iteration 1852/ 3814 | consumed samples: 948224 | consumed tokens: 1941962752 | elapsed time per iteration (s): 6.01 | learning rate: 3.149E-04 | global batch size: 512 | lm loss: 3.549187E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.149 | TFLOPs: 64.31 | +[default7]: iteration 1853/ 3814 | consumed samples: 948736 | consumed tokens: 1943011328 | elapsed time per iteration (s): 6.12 | learning rate: 3.147E-04 | global batch size: 512 | lm loss: 3.559198E+00 | loss scale: 32768.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.611 | TFLOPs: 63.15 | +[default7]: iteration 1854/ 3814 | consumed samples: 949248 | consumed tokens: 1944059904 | elapsed time per iteration (s): 6.11 | learning rate: 3.144E-04 | global batch size: 512 | lm loss: 3.569708E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.822 | TFLOPs: 63.31 | +[default7]: iteration 1855/ 3814 | consumed samples: 949760 | consumed tokens: 1945108480 | elapsed time per iteration (s): 6.20 | learning rate: 3.142E-04 | global batch size: 512 | lm loss: 3.553577E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.628 | TFLOPs: 62.41 | +[default7]: iteration 1856/ 3814 | consumed samples: 950272 | consumed tokens: 1946157056 | elapsed time per iteration (s): 6.02 | learning rate: 3.140E-04 | global batch size: 512 | lm loss: 3.525123E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.055 | TFLOPs: 64.24 | +[default7]: iteration 1857/ 3814 | consumed samples: 950784 | consumed tokens: 1947205632 | elapsed time per iteration (s): 5.95 | learning rate: 3.138E-04 | global batch size: 512 | lm loss: 3.529348E+00 | loss scale: 32768.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.011 | TFLOPs: 64.96 | +[default7]: iteration 1858/ 3814 | consumed samples: 951296 | consumed tokens: 1948254208 | elapsed time per iteration (s): 6.11 | learning rate: 3.135E-04 | global batch size: 512 | lm loss: 3.574072E+00 | loss scale: 32768.0 | grad norm: 0.164 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.779 | TFLOPs: 63.28 | +[default7]: iteration 1859/ 3814 | consumed samples: 951808 | consumed tokens: 1949302784 | elapsed time per iteration (s): 6.06 | learning rate: 3.133E-04 | global batch size: 512 | lm loss: 3.534303E+00 | loss scale: 32768.0 | grad norm: 0.186 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.421 | TFLOPs: 63.76 | +[default7]: iteration 1860/ 3814 | consumed samples: 952320 | consumed tokens: 1950351360 | elapsed time per iteration (s): 5.98 | learning rate: 3.131E-04 | global batch size: 512 | lm loss: 3.553441E+00 | loss scale: 32768.0 | grad norm: 0.182 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.580 | TFLOPs: 64.64 | +[default7]: iteration 1861/ 3814 | consumed samples: 952832 | consumed tokens: 1951399936 | elapsed time per iteration (s): 6.07 | learning rate: 3.128E-04 | global batch size: 512 | lm loss: 3.525907E+00 | loss scale: 32768.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.411 | TFLOPs: 63.76 | +[default7]: iteration 1862/ 3814 | consumed samples: 953344 | consumed tokens: 1952448512 | elapsed time per iteration (s): 6.10 | learning rate: 3.126E-04 | global batch size: 512 | lm loss: 3.543019E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.884 | TFLOPs: 63.36 | +[default7]: iteration 1863/ 3814 | consumed samples: 953856 | consumed tokens: 1953497088 | elapsed time per iteration (s): 5.99 | learning rate: 3.124E-04 | global batch size: 512 | lm loss: 3.556461E+00 | loss scale: 32768.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.473 | TFLOPs: 64.56 | +[default7]: iteration 1864/ 3814 | consumed samples: 954368 | consumed tokens: 1954545664 | elapsed time per iteration (s): 5.98 | learning rate: 3.121E-04 | global batch size: 512 | lm loss: 3.539651E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.631 | TFLOPs: 64.68 | +[default7]: iteration 1865/ 3814 | consumed samples: 954880 | consumed tokens: 1955594240 | elapsed time per iteration (s): 5.98 | learning rate: 3.119E-04 | global batch size: 512 | lm loss: 3.547019E+00 | loss scale: 32768.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.565 | TFLOPs: 64.63 | +[default7]: iteration 1866/ 3814 | consumed samples: 955392 | consumed tokens: 1956642816 | elapsed time per iteration (s): 6.01 | learning rate: 3.117E-04 | global batch size: 512 | lm loss: 3.539239E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.214 | TFLOPs: 64.36 | +[default7]: iteration 1867/ 3814 | consumed samples: 955904 | consumed tokens: 1957691392 | elapsed time per iteration (s): 5.97 | learning rate: 3.114E-04 | global batch size: 512 | lm loss: 3.540428E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.818 | TFLOPs: 64.82 | +[default7]: iteration 1868/ 3814 | consumed samples: 956416 | consumed tokens: 1958739968 | elapsed time per iteration (s): 5.98 | learning rate: 3.112E-04 | global batch size: 512 | lm loss: 3.551434E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.594 | TFLOPs: 64.65 | +[default7]: iteration 1869/ 3814 | consumed samples: 956928 | consumed tokens: 1959788544 | elapsed time per iteration (s): 5.96 | learning rate: 3.110E-04 | global batch size: 512 | lm loss: 3.553380E+00 | loss scale: 32768.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.863 | TFLOPs: 64.85 | +[default7]: iteration 1870/ 3814 | consumed samples: 957440 | consumed tokens: 1960837120 | elapsed time per iteration (s): 6.10 | learning rate: 3.107E-04 | global batch size: 512 | lm loss: 3.503360E+00 | loss scale: 32768.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.920 | TFLOPs: 63.39 | +[default7]: iteration 1871/ 3814 | consumed samples: 957952 | consumed tokens: 1961885696 | elapsed time per iteration (s): 5.99 | learning rate: 3.105E-04 | global batch size: 512 | lm loss: 3.532348E+00 | loss scale: 32768.0 | grad norm: 0.100 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.436 | TFLOPs: 64.53 | +[default7]: iteration 1872/ 3814 | consumed samples: 958464 | consumed tokens: 1962934272 | elapsed time per iteration (s): 6.18 | learning rate: 3.103E-04 | global batch size: 512 | lm loss: 3.518601E+00 | loss scale: 32768.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.887 | TFLOPs: 62.61 | +[default7]: iteration 1873/ 3814 | consumed samples: 958976 | consumed tokens: 1963982848 | elapsed time per iteration (s): 5.97 | learning rate: 3.101E-04 | global batch size: 512 | lm loss: 3.568210E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.759 | TFLOPs: 64.77 | +[default7]: iteration 1874/ 3814 | consumed samples: 959488 | consumed tokens: 1965031424 | elapsed time per iteration (s): 6.02 | learning rate: 3.098E-04 | global batch size: 512 | lm loss: 3.535143E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.080 | TFLOPs: 64.26 | +[default7]: iteration 1875/ 3814 | consumed samples: 960000 | consumed tokens: 1966080000 | elapsed time per iteration (s): 5.98 | learning rate: 3.096E-04 | global batch size: 512 | lm loss: 3.558394E+00 | loss scale: 32768.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.676 | TFLOPs: 64.71 | +[default7]: iteration 1876/ 3814 | consumed samples: 960512 | consumed tokens: 1967128576 | elapsed time per iteration (s): 6.17 | learning rate: 3.094E-04 | global batch size: 512 | lm loss: 3.543514E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.965 | TFLOPs: 62.66 | +[default7]: iteration 1877/ 3814 | consumed samples: 961024 | consumed tokens: 1968177152 | elapsed time per iteration (s): 6.30 | learning rate: 3.091E-04 | global batch size: 512 | lm loss: 3.531677E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.224 | TFLOPs: 61.35 | +[default7]: iteration 1878/ 3814 | consumed samples: 961536 | consumed tokens: 1969225728 | elapsed time per iteration (s): 6.01 | learning rate: 3.089E-04 | global batch size: 512 | lm loss: 3.522252E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.167 | TFLOPs: 64.33 | +[default7]: iteration 1879/ 3814 | consumed samples: 962048 | consumed tokens: 1970274304 | elapsed time per iteration (s): 5.93 | learning rate: 3.087E-04 | global batch size: 512 | lm loss: 3.522957E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.363 | TFLOPs: 65.23 | +[default7]: iteration 1880/ 3814 | consumed samples: 962560 | consumed tokens: 1971322880 | elapsed time per iteration (s): 6.01 | learning rate: 3.084E-04 | global batch size: 512 | lm loss: 3.568793E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.163 | TFLOPs: 64.32 | +[default7]: iteration 1881/ 3814 | consumed samples: 963072 | consumed tokens: 1972371456 | elapsed time per iteration (s): 6.02 | learning rate: 3.082E-04 | global batch size: 512 | lm loss: 3.557672E+00 | loss scale: 32768.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.114 | TFLOPs: 64.29 | +[default7]: iteration 1882/ 3814 | consumed samples: 963584 | consumed tokens: 1973420032 | elapsed time per iteration (s): 5.93 | learning rate: 3.080E-04 | global batch size: 512 | lm loss: 3.534809E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.350 | TFLOPs: 65.22 | +[default7]: iteration 1883/ 3814 | consumed samples: 964096 | consumed tokens: 1974468608 | elapsed time per iteration (s): 6.00 | learning rate: 3.077E-04 | global batch size: 512 | lm loss: 3.529591E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.402 | TFLOPs: 64.50 | +[default7]: iteration 1884/ 3814 | consumed samples: 964608 | consumed tokens: 1975517184 | elapsed time per iteration (s): 5.95 | learning rate: 3.075E-04 | global batch size: 512 | lm loss: 3.547356E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.103 | TFLOPs: 65.03 | +[default7]: iteration 1885/ 3814 | consumed samples: 965120 | consumed tokens: 1976565760 | elapsed time per iteration (s): 5.95 | learning rate: 3.073E-04 | global batch size: 512 | lm loss: 3.558697E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.042 | TFLOPs: 64.99 | +[default7]: iteration 1886/ 3814 | consumed samples: 965632 | consumed tokens: 1977614336 | elapsed time per iteration (s): 5.92 | learning rate: 3.070E-04 | global batch size: 512 | lm loss: 3.527710E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.444 | TFLOPs: 65.29 | +[default7]: iteration 1887/ 3814 | consumed samples: 966144 | consumed tokens: 1978662912 | elapsed time per iteration (s): 5.96 | learning rate: 3.068E-04 | global batch size: 512 | lm loss: 3.555336E+00 | loss scale: 32768.0 | grad norm: 0.166 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.867 | TFLOPs: 64.86 | +[default7]: iteration 1888/ 3814 | consumed samples: 966656 | consumed tokens: 1979711488 | elapsed time per iteration (s): 6.03 | learning rate: 3.066E-04 | global batch size: 512 | lm loss: 3.553968E+00 | loss scale: 32768.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.881 | TFLOPs: 64.11 | +[default7]: iteration 1889/ 3814 | consumed samples: 967168 | consumed tokens: 1980760064 | elapsed time per iteration (s): 6.03 | learning rate: 3.063E-04 | global batch size: 512 | lm loss: 3.529797E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.945 | TFLOPs: 64.16 | +[default7]: iteration 1890/ 3814 | consumed samples: 967680 | consumed tokens: 1981808640 | elapsed time per iteration (s): 5.99 | learning rate: 3.061E-04 | global batch size: 512 | lm loss: 3.548388E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.421 | TFLOPs: 64.52 | +[default7]: iteration 1891/ 3814 | consumed samples: 968192 | consumed tokens: 1982857216 | elapsed time per iteration (s): 6.02 | learning rate: 3.059E-04 | global batch size: 512 | lm loss: 3.529384E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.038 | TFLOPs: 64.23 | +[default7]: iteration 1892/ 3814 | consumed samples: 968704 | consumed tokens: 1983905792 | elapsed time per iteration (s): 5.94 | learning rate: 3.056E-04 | global batch size: 512 | lm loss: 3.572591E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.245 | TFLOPs: 65.14 | +[default7]: iteration 1893/ 3814 | consumed samples: 969216 | consumed tokens: 1984954368 | elapsed time per iteration (s): 5.95 | learning rate: 3.054E-04 | global batch size: 512 | lm loss: 3.520608E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.980 | TFLOPs: 64.94 | +[default7]: iteration 1894/ 3814 | consumed samples: 969728 | consumed tokens: 1986002944 | elapsed time per iteration (s): 5.86 | learning rate: 3.052E-04 | global batch size: 512 | lm loss: 3.533462E+00 | loss scale: 32768.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.403 | TFLOPs: 66.02 | +[default7]: iteration 1895/ 3814 | consumed samples: 970240 | consumed tokens: 1987051520 | elapsed time per iteration (s): 6.04 | learning rate: 3.049E-04 | global batch size: 512 | lm loss: 3.527530E+00 | loss scale: 32768.0 | grad norm: 0.102 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.736 | TFLOPs: 64.00 | +[default7]: iteration 1896/ 3814 | consumed samples: 970752 | consumed tokens: 1988100096 | elapsed time per iteration (s): 5.99 | learning rate: 3.047E-04 | global batch size: 512 | lm loss: 3.562495E+00 | loss scale: 32768.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.523 | TFLOPs: 64.60 | +[default7]: iteration 1897/ 3814 | consumed samples: 971264 | consumed tokens: 1989148672 | elapsed time per iteration (s): 5.89 | learning rate: 3.045E-04 | global batch size: 512 | lm loss: 3.536178E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.875 | TFLOPs: 65.62 | +[default7]: iteration 1898/ 3814 | consumed samples: 971776 | consumed tokens: 1990197248 | elapsed time per iteration (s): 6.02 | learning rate: 3.042E-04 | global batch size: 512 | lm loss: 3.553028E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.997 | TFLOPs: 64.20 | +[default7]: iteration 1899/ 3814 | consumed samples: 972288 | consumed tokens: 1991245824 | elapsed time per iteration (s): 5.98 | learning rate: 3.040E-04 | global batch size: 512 | lm loss: 3.526186E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.575 | TFLOPs: 64.64 | +[default7]: iteration 1900/ 3814 | consumed samples: 972800 | consumed tokens: 1992294400 | elapsed time per iteration (s): 6.01 | learning rate: 3.038E-04 | global batch size: 512 | lm loss: 3.516155E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.233 | TFLOPs: 64.38 | +[default7]: iteration 1901/ 3814 | consumed samples: 973312 | consumed tokens: 1993342976 | elapsed time per iteration (s): 6.03 | learning rate: 3.035E-04 | global batch size: 512 | lm loss: 3.513262E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.962 | TFLOPs: 64.17 | +[default7]: iteration 1902/ 3814 | consumed samples: 973824 | consumed tokens: 1994391552 | elapsed time per iteration (s): 5.90 | learning rate: 3.033E-04 | global batch size: 512 | lm loss: 3.545250E+00 | loss scale: 32768.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.756 | TFLOPs: 65.53 | +[default7]: iteration 1903/ 3814 | consumed samples: 974336 | consumed tokens: 1995440128 | elapsed time per iteration (s): 5.99 | learning rate: 3.031E-04 | global batch size: 512 | lm loss: 3.531533E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.503 | TFLOPs: 64.58 | +[default7]: iteration 1904/ 3814 | consumed samples: 974848 | consumed tokens: 1996488704 | elapsed time per iteration (s): 5.99 | learning rate: 3.028E-04 | global batch size: 512 | lm loss: 3.525655E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.424 | TFLOPs: 64.52 | +[default7]: iteration 1905/ 3814 | consumed samples: 975360 | consumed tokens: 1997537280 | elapsed time per iteration (s): 6.02 | learning rate: 3.026E-04 | global batch size: 512 | lm loss: 3.562680E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.094 | TFLOPs: 64.27 | +[default7]: iteration 1906/ 3814 | consumed samples: 975872 | consumed tokens: 1998585856 | elapsed time per iteration (s): 5.96 | learning rate: 3.024E-04 | global batch size: 512 | lm loss: 3.520728E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.861 | TFLOPs: 64.85 | +[default7]: iteration 1907/ 3814 | consumed samples: 976384 | consumed tokens: 1999634432 | elapsed time per iteration (s): 5.96 | learning rate: 3.021E-04 | global batch size: 512 | lm loss: 3.528896E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.946 | TFLOPs: 64.92 | +[default7]: iteration 1908/ 3814 | consumed samples: 976896 | consumed tokens: 2000683008 | elapsed time per iteration (s): 5.92 | learning rate: 3.019E-04 | global batch size: 512 | lm loss: 3.570657E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.496 | TFLOPs: 65.33 | +[default7]: iteration 1909/ 3814 | consumed samples: 977408 | consumed tokens: 2001731584 | elapsed time per iteration (s): 6.02 | learning rate: 3.017E-04 | global batch size: 512 | lm loss: 3.549084E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.091 | TFLOPs: 64.27 | +[default7]: iteration 1910/ 3814 | consumed samples: 977920 | consumed tokens: 2002780160 | elapsed time per iteration (s): 6.02 | learning rate: 3.014E-04 | global batch size: 512 | lm loss: 3.537117E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.984 | TFLOPs: 64.19 | +[default7]: iteration 1911/ 3814 | consumed samples: 978432 | consumed tokens: 2003828736 | elapsed time per iteration (s): 5.96 | learning rate: 3.012E-04 | global batch size: 512 | lm loss: 3.510883E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.861 | TFLOPs: 64.85 | +[default7]: iteration 1912/ 3814 | consumed samples: 978944 | consumed tokens: 2004877312 | elapsed time per iteration (s): 5.98 | learning rate: 3.010E-04 | global batch size: 512 | lm loss: 3.523769E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.584 | TFLOPs: 64.64 | +[default7]: iteration 1913/ 3814 | consumed samples: 979456 | consumed tokens: 2005925888 | elapsed time per iteration (s): 5.99 | learning rate: 3.007E-04 | global batch size: 512 | lm loss: 3.522243E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.513 | TFLOPs: 64.59 | +[default7]: iteration 1914/ 3814 | consumed samples: 979968 | consumed tokens: 2006974464 | elapsed time per iteration (s): 5.74 | learning rate: 3.005E-04 | global batch size: 512 | lm loss: 3.531323E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.260 | TFLOPs: 67.42 | +[default7]: iteration 1915/ 3814 | consumed samples: 980480 | consumed tokens: 2008023040 | elapsed time per iteration (s): 5.99 | learning rate: 3.003E-04 | global batch size: 512 | lm loss: 3.511978E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.414 | TFLOPs: 64.51 | +[default7]: iteration 1916/ 3814 | consumed samples: 980992 | consumed tokens: 2009071616 | elapsed time per iteration (s): 5.95 | learning rate: 3.000E-04 | global batch size: 512 | lm loss: 3.501088E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.048 | TFLOPs: 64.99 | +[default7]: iteration 1917/ 3814 | consumed samples: 981504 | consumed tokens: 2010120192 | elapsed time per iteration (s): 5.97 | learning rate: 2.998E-04 | global batch size: 512 | lm loss: 3.544541E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.705 | TFLOPs: 64.73 | +[default7]: iteration 1918/ 3814 | consumed samples: 982016 | consumed tokens: 2011168768 | elapsed time per iteration (s): 5.97 | learning rate: 2.996E-04 | global batch size: 512 | lm loss: 3.510235E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.825 | TFLOPs: 64.82 | +[default7]: iteration 1919/ 3814 | consumed samples: 982528 | consumed tokens: 2012217344 | elapsed time per iteration (s): 5.97 | learning rate: 2.993E-04 | global batch size: 512 | lm loss: 3.477947E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.724 | TFLOPs: 64.75 | +[default7]: iteration 1920/ 3814 | consumed samples: 983040 | consumed tokens: 2013265920 | elapsed time per iteration (s): 6.01 | learning rate: 2.991E-04 | global batch size: 512 | lm loss: 3.525810E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.137 | TFLOPs: 64.30 | +[default7]: iteration 1921/ 3814 | consumed samples: 983552 | consumed tokens: 2014314496 | elapsed time per iteration (s): 6.03 | learning rate: 2.989E-04 | global batch size: 512 | lm loss: 3.523257E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.949 | TFLOPs: 64.16 | +[default7]: iteration 1922/ 3814 | consumed samples: 984064 | consumed tokens: 2015363072 | elapsed time per iteration (s): 6.00 | learning rate: 2.986E-04 | global batch size: 512 | lm loss: 3.531442E+00 | loss scale: 32768.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.327 | TFLOPs: 64.45 | +[default7]: iteration 1923/ 3814 | consumed samples: 984576 | consumed tokens: 2016411648 | elapsed time per iteration (s): 5.92 | learning rate: 2.984E-04 | global batch size: 512 | lm loss: 3.509567E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.434 | TFLOPs: 65.28 | +[default7]: iteration 1924/ 3814 | consumed samples: 985088 | consumed tokens: 2017460224 | elapsed time per iteration (s): 6.00 | learning rate: 2.982E-04 | global batch size: 512 | lm loss: 3.559988E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.327 | TFLOPs: 64.45 | +[default7]: iteration 1925/ 3814 | consumed samples: 985600 | consumed tokens: 2018508800 | elapsed time per iteration (s): 5.94 | learning rate: 2.979E-04 | global batch size: 512 | lm loss: 3.546054E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.171 | TFLOPs: 65.09 | +[default7]: iteration 1926/ 3814 | consumed samples: 986112 | consumed tokens: 2019557376 | elapsed time per iteration (s): 5.97 | learning rate: 2.977E-04 | global batch size: 512 | lm loss: 3.529557E+00 | loss scale: 32768.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.743 | TFLOPs: 64.76 | +[default7]: iteration 1927/ 3814 | consumed samples: 986624 | consumed tokens: 2020605952 | elapsed time per iteration (s): 5.96 | learning rate: 2.975E-04 | global batch size: 512 | lm loss: 3.523864E+00 | loss scale: 32768.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.896 | TFLOPs: 64.88 | +[default7]: iteration 1928/ 3814 | consumed samples: 987136 | consumed tokens: 2021654528 | elapsed time per iteration (s): 6.00 | learning rate: 2.972E-04 | global batch size: 512 | lm loss: 3.552786E+00 | loss scale: 32768.0 | grad norm: 0.163 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.308 | TFLOPs: 64.43 | +[default7]: iteration 1929/ 3814 | consumed samples: 987648 | consumed tokens: 2022703104 | elapsed time per iteration (s): 5.97 | learning rate: 2.970E-04 | global batch size: 512 | lm loss: 3.511624E+00 | loss scale: 32768.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.814 | TFLOPs: 64.82 | +[default7]: iteration 1930/ 3814 | consumed samples: 988160 | consumed tokens: 2023751680 | elapsed time per iteration (s): 6.00 | learning rate: 2.968E-04 | global batch size: 512 | lm loss: 3.531063E+00 | loss scale: 32768.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.394 | TFLOPs: 64.50 | +[default7]: iteration 1931/ 3814 | consumed samples: 988672 | consumed tokens: 2024800256 | elapsed time per iteration (s): 6.03 | learning rate: 2.965E-04 | global batch size: 512 | lm loss: 3.493126E+00 | loss scale: 32768.0 | grad norm: 0.177 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.979 | TFLOPs: 64.19 | +[default7]: iteration 1932/ 3814 | consumed samples: 989184 | consumed tokens: 2025848832 | elapsed time per iteration (s): 5.97 | learning rate: 2.963E-04 | global batch size: 512 | lm loss: 3.528163E+00 | loss scale: 32768.0 | grad norm: 0.171 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.743 | TFLOPs: 64.76 | +[default7]: iteration 1933/ 3814 | consumed samples: 989696 | consumed tokens: 2026897408 | elapsed time per iteration (s): 5.98 | learning rate: 2.961E-04 | global batch size: 512 | lm loss: 3.576891E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.572 | TFLOPs: 64.63 | +[default7]: iteration 1934/ 3814 | consumed samples: 990208 | consumed tokens: 2027945984 | elapsed time per iteration (s): 6.01 | learning rate: 2.958E-04 | global batch size: 512 | lm loss: 3.510211E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.197 | TFLOPs: 64.35 | +[default7]: iteration 1935/ 3814 | consumed samples: 990720 | consumed tokens: 2028994560 | elapsed time per iteration (s): 6.03 | learning rate: 2.956E-04 | global batch size: 512 | lm loss: 3.511155E+00 | loss scale: 32768.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.966 | TFLOPs: 64.18 | +[default7]: iteration 1936/ 3814 | consumed samples: 991232 | consumed tokens: 2030043136 | elapsed time per iteration (s): 6.01 | learning rate: 2.954E-04 | global batch size: 512 | lm loss: 3.540241E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.202 | TFLOPs: 64.35 | +[default7]: iteration 1937/ 3814 | consumed samples: 991744 | consumed tokens: 2031091712 | elapsed time per iteration (s): 5.99 | learning rate: 2.951E-04 | global batch size: 512 | lm loss: 3.507184E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.513 | TFLOPs: 64.59 | +[default7]: iteration 1938/ 3814 | consumed samples: 992256 | consumed tokens: 2032140288 | elapsed time per iteration (s): 5.97 | learning rate: 2.949E-04 | global batch size: 512 | lm loss: 3.538493E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.750 | TFLOPs: 64.77 | +[default7]: iteration 1939/ 3814 | consumed samples: 992768 | consumed tokens: 2033188864 | elapsed time per iteration (s): 6.00 | learning rate: 2.947E-04 | global batch size: 512 | lm loss: 3.510516E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.393 | TFLOPs: 64.50 | +[default7]: iteration 1940/ 3814 | consumed samples: 993280 | consumed tokens: 2034237440 | elapsed time per iteration (s): 5.92 | learning rate: 2.944E-04 | global batch size: 512 | lm loss: 3.513529E+00 | loss scale: 32768.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.468 | TFLOPs: 65.31 | +[default7]: iteration 1941/ 3814 | consumed samples: 993792 | consumed tokens: 2035286016 | elapsed time per iteration (s): 5.99 | learning rate: 2.942E-04 | global batch size: 512 | lm loss: 3.496787E+00 | loss scale: 32768.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.408 | TFLOPs: 64.51 | +[default7]: iteration 1942/ 3814 | consumed samples: 994304 | consumed tokens: 2036334592 | elapsed time per iteration (s): 6.00 | learning rate: 2.940E-04 | global batch size: 512 | lm loss: 3.535803E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.386 | TFLOPs: 64.49 | +[default7]: iteration 1943/ 3814 | consumed samples: 994816 | consumed tokens: 2037383168 | elapsed time per iteration (s): 5.98 | learning rate: 2.937E-04 | global batch size: 512 | lm loss: 3.528340E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.597 | TFLOPs: 64.65 | +[default7]: iteration 1944/ 3814 | consumed samples: 995328 | consumed tokens: 2038431744 | elapsed time per iteration (s): 6.00 | learning rate: 2.935E-04 | global batch size: 512 | lm loss: 3.561000E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.350 | TFLOPs: 64.47 | +[default7]: iteration 1945/ 3814 | consumed samples: 995840 | consumed tokens: 2039480320 | elapsed time per iteration (s): 6.00 | learning rate: 2.933E-04 | global batch size: 512 | lm loss: 3.544464E+00 | loss scale: 32768.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.282 | TFLOPs: 64.41 | +[default7]: iteration 1946/ 3814 | consumed samples: 996352 | consumed tokens: 2040528896 | elapsed time per iteration (s): 5.99 | learning rate: 2.930E-04 | global batch size: 512 | lm loss: 3.500131E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.505 | TFLOPs: 64.58 | +[default7]: iteration 1947/ 3814 | consumed samples: 996864 | consumed tokens: 2041577472 | elapsed time per iteration (s): 6.04 | learning rate: 2.928E-04 | global batch size: 512 | lm loss: 3.508358E+00 | loss scale: 32768.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.741 | TFLOPs: 64.01 | +[default7]: iteration 1948/ 3814 | consumed samples: 997376 | consumed tokens: 2042626048 | elapsed time per iteration (s): 6.03 | learning rate: 2.926E-04 | global batch size: 512 | lm loss: 3.511284E+00 | loss scale: 32768.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.952 | TFLOPs: 64.16 | +[default7]: iteration 1949/ 3814 | consumed samples: 997888 | consumed tokens: 2043674624 | elapsed time per iteration (s): 5.96 | learning rate: 2.923E-04 | global batch size: 512 | lm loss: 3.526766E+00 | loss scale: 32768.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.842 | TFLOPs: 64.84 | +[default7]: iteration 1950/ 3814 | consumed samples: 998400 | consumed tokens: 2044723200 | elapsed time per iteration (s): 6.00 | learning rate: 2.921E-04 | global batch size: 512 | lm loss: 3.499235E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.318 | TFLOPs: 64.44 | +[default7]: iteration 1951/ 3814 | consumed samples: 998912 | consumed tokens: 2045771776 | elapsed time per iteration (s): 5.95 | learning rate: 2.919E-04 | global batch size: 512 | lm loss: 3.506357E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.001 | TFLOPs: 64.96 | +[default7]: iteration 1952/ 3814 | consumed samples: 999424 | consumed tokens: 2046820352 | elapsed time per iteration (s): 5.90 | learning rate: 2.916E-04 | global batch size: 512 | lm loss: 3.524409E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.729 | TFLOPs: 65.51 | +[default7]: iteration 1953/ 3814 | consumed samples: 999936 | consumed tokens: 2047868928 | elapsed time per iteration (s): 5.98 | learning rate: 2.914E-04 | global batch size: 512 | lm loss: 3.515661E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.610 | TFLOPs: 64.66 | +[default7]: iteration 1954/ 3814 | consumed samples: 1000448 | consumed tokens: 2048917504 | elapsed time per iteration (s): 6.00 | learning rate: 2.912E-04 | global batch size: 512 | lm loss: 3.514559E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.401 | TFLOPs: 64.50 | +[default7]: iteration 1955/ 3814 | consumed samples: 1000960 | consumed tokens: 2049966080 | elapsed time per iteration (s): 6.01 | learning rate: 2.909E-04 | global batch size: 512 | lm loss: 3.504758E+00 | loss scale: 32768.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.172 | TFLOPs: 64.33 | +[default7]: iteration 1956/ 3814 | consumed samples: 1001472 | consumed tokens: 2051014656 | elapsed time per iteration (s): 6.00 | learning rate: 2.907E-04 | global batch size: 512 | lm loss: 3.516576E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.267 | TFLOPs: 64.40 | +[default7]: iteration 1957/ 3814 | consumed samples: 1001984 | consumed tokens: 2052063232 | elapsed time per iteration (s): 5.98 | learning rate: 2.904E-04 | global batch size: 512 | lm loss: 3.522459E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.678 | TFLOPs: 64.71 | +[default7]: iteration 1958/ 3814 | consumed samples: 1002496 | consumed tokens: 2053111808 | elapsed time per iteration (s): 6.05 | learning rate: 2.902E-04 | global batch size: 512 | lm loss: 3.498356E+00 | loss scale: 32768.0 | grad norm: 0.143 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.592 | TFLOPs: 63.89 | +[default7]: iteration 1959/ 3814 | consumed samples: 1003008 | consumed tokens: 2054160384 | elapsed time per iteration (s): 5.90 | learning rate: 2.900E-04 | global batch size: 512 | lm loss: 3.531790E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.774 | TFLOPs: 65.54 | +[default7]: iteration 1960/ 3814 | consumed samples: 1003520 | consumed tokens: 2055208960 | elapsed time per iteration (s): 5.95 | learning rate: 2.897E-04 | global batch size: 512 | lm loss: 3.525578E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.055 | TFLOPs: 65.00 | +[default7]: iteration 1961/ 3814 | consumed samples: 1004032 | consumed tokens: 2056257536 | elapsed time per iteration (s): 6.05 | learning rate: 2.895E-04 | global batch size: 512 | lm loss: 3.519659E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.669 | TFLOPs: 63.95 | +[default7]: iteration 1962/ 3814 | consumed samples: 1004544 | consumed tokens: 2057306112 | elapsed time per iteration (s): 6.20 | learning rate: 2.893E-04 | global batch size: 512 | lm loss: 3.506843E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.642 | TFLOPs: 62.42 | +[default7]: iteration 1963/ 3814 | consumed samples: 1005056 | consumed tokens: 2058354688 | elapsed time per iteration (s): 6.14 | learning rate: 2.890E-04 | global batch size: 512 | lm loss: 3.483857E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.372 | TFLOPs: 62.97 | +[default7]: iteration 1964/ 3814 | consumed samples: 1005568 | consumed tokens: 2059403264 | elapsed time per iteration (s): 6.18 | learning rate: 2.888E-04 | global batch size: 512 | lm loss: 3.492384E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.830 | TFLOPs: 62.56 | +[default7]: iteration 1965/ 3814 | consumed samples: 1006080 | consumed tokens: 2060451840 | elapsed time per iteration (s): 6.13 | learning rate: 2.886E-04 | global batch size: 512 | lm loss: 3.521236E+00 | loss scale: 32768.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.586 | TFLOPs: 63.13 | +[default7]: iteration 1966/ 3814 | consumed samples: 1006592 | consumed tokens: 2061500416 | elapsed time per iteration (s): 6.29 | learning rate: 2.883E-04 | global batch size: 512 | lm loss: 3.461640E+00 | loss scale: 32768.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.388 | TFLOPs: 61.47 | +[default7]: iteration 1967/ 3814 | consumed samples: 1007104 | consumed tokens: 2062548992 | elapsed time per iteration (s): 6.12 | learning rate: 2.881E-04 | global batch size: 512 | lm loss: 3.531657E+00 | loss scale: 32768.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.713 | TFLOPs: 63.23 | +[default7]: iteration 1968/ 3814 | consumed samples: 1007616 | consumed tokens: 2063597568 | elapsed time per iteration (s): 6.20 | learning rate: 2.879E-04 | global batch size: 512 | lm loss: 3.489229E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.604 | TFLOPs: 62.39 | +[default7]: iteration 1969/ 3814 | consumed samples: 1008128 | consumed tokens: 2064646144 | elapsed time per iteration (s): 6.10 | learning rate: 2.876E-04 | global batch size: 512 | lm loss: 3.479550E+00 | loss scale: 32768.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.904 | TFLOPs: 63.37 | +[default7]: iteration 1970/ 3814 | consumed samples: 1008640 | consumed tokens: 2065694720 | elapsed time per iteration (s): 6.24 | learning rate: 2.874E-04 | global batch size: 512 | lm loss: 3.504084E+00 | loss scale: 32768.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.016 | TFLOPs: 61.95 | +[default7]: iteration 1971/ 3814 | consumed samples: 1009152 | consumed tokens: 2066743296 | elapsed time per iteration (s): 6.22 | learning rate: 2.872E-04 | global batch size: 512 | lm loss: 3.496452E+00 | loss scale: 32768.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.359 | TFLOPs: 62.21 | +[default7]: iteration 1972/ 3814 | consumed samples: 1009664 | consumed tokens: 2067791872 | elapsed time per iteration (s): 6.07 | learning rate: 2.869E-04 | global batch size: 512 | lm loss: 3.480484E+00 | loss scale: 32768.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.366 | TFLOPs: 63.72 | +[default7]: iteration 1973/ 3814 | consumed samples: 1010176 | consumed tokens: 2068840448 | elapsed time per iteration (s): 5.98 | learning rate: 2.867E-04 | global batch size: 512 | lm loss: 3.506086E+00 | loss scale: 32768.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.583 | TFLOPs: 64.64 | +[default7]: iteration 1974/ 3814 | consumed samples: 1010688 | consumed tokens: 2069889024 | elapsed time per iteration (s): 6.16 | learning rate: 2.865E-04 | global batch size: 512 | lm loss: 3.553682E+00 | loss scale: 32768.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.097 | TFLOPs: 62.76 | +[default7]: iteration 1975/ 3814 | consumed samples: 1011200 | consumed tokens: 2070937600 | elapsed time per iteration (s): 6.21 | learning rate: 2.862E-04 | global batch size: 512 | lm loss: 3.504672E+00 | loss scale: 32768.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.481 | TFLOPs: 62.30 | +[default7]: iteration 1976/ 3814 | consumed samples: 1011712 | consumed tokens: 2071986176 | elapsed time per iteration (s): 6.16 | learning rate: 2.860E-04 | global batch size: 512 | lm loss: 3.499836E+00 | loss scale: 32768.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.053 | TFLOPs: 62.73 | +[default7]: iteration 1977/ 3814 | consumed samples: 1012224 | consumed tokens: 2073034752 | elapsed time per iteration (s): 6.18 | learning rate: 2.857E-04 | global batch size: 512 | lm loss: 3.514017E+00 | loss scale: 32768.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.838 | TFLOPs: 62.57 | +[default7]: iteration 1978/ 3814 | consumed samples: 1012736 | consumed tokens: 2074083328 | elapsed time per iteration (s): 6.17 | learning rate: 2.855E-04 | global batch size: 512 | lm loss: 3.494487E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.032 | TFLOPs: 62.72 | +[default7]: iteration 1979/ 3814 | consumed samples: 1013248 | consumed tokens: 2075131904 | elapsed time per iteration (s): 6.15 | learning rate: 2.853E-04 | global batch size: 512 | lm loss: 3.519239E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.292 | TFLOPs: 62.91 | +[default7]: iteration 1980/ 3814 | consumed samples: 1013760 | consumed tokens: 2076180480 | elapsed time per iteration (s): 6.25 | learning rate: 2.850E-04 | global batch size: 512 | lm loss: 3.491620E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.912 | TFLOPs: 61.87 | +[default7]: iteration 1981/ 3814 | consumed samples: 1014272 | consumed tokens: 2077229056 | elapsed time per iteration (s): 6.07 | learning rate: 2.848E-04 | global batch size: 512 | lm loss: 3.465417E+00 | loss scale: 32768.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.405 | TFLOPs: 63.75 | +[default7]: iteration 1982/ 3814 | consumed samples: 1014784 | consumed tokens: 2078277632 | elapsed time per iteration (s): 5.96 | learning rate: 2.846E-04 | global batch size: 512 | lm loss: 3.528672E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.933 | TFLOPs: 64.91 | +[default7]: iteration 1983/ 3814 | consumed samples: 1015296 | consumed tokens: 2079326208 | elapsed time per iteration (s): 6.19 | learning rate: 2.843E-04 | global batch size: 512 | lm loss: 3.524416E+00 | loss scale: 32768.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.728 | TFLOPs: 62.49 | +[default7]: iteration 1984/ 3814 | consumed samples: 1015808 | consumed tokens: 2080374784 | elapsed time per iteration (s): 6.13 | learning rate: 2.841E-04 | global batch size: 512 | lm loss: 3.496377E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.530 | TFLOPs: 63.09 | +[default7]: iteration 1985/ 3814 | consumed samples: 1016320 | consumed tokens: 2081423360 | elapsed time per iteration (s): 6.15 | learning rate: 2.839E-04 | global batch size: 512 | lm loss: 3.510069E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.282 | TFLOPs: 62.90 | +[default7]: iteration 1986/ 3814 | consumed samples: 1016832 | consumed tokens: 2082471936 | elapsed time per iteration (s): 6.17 | learning rate: 2.836E-04 | global batch size: 512 | lm loss: 3.486971E+00 | loss scale: 32768.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.931 | TFLOPs: 62.64 | +[default7]: iteration 1987/ 3814 | consumed samples: 1017344 | consumed tokens: 2083520512 | elapsed time per iteration (s): 6.06 | learning rate: 2.834E-04 | global batch size: 512 | lm loss: 3.493435E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.496 | TFLOPs: 63.82 | +[default7]: iteration 1988/ 3814 | consumed samples: 1017856 | consumed tokens: 2084569088 | elapsed time per iteration (s): 6.20 | learning rate: 2.832E-04 | global batch size: 512 | lm loss: 3.495522E+00 | loss scale: 32768.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.612 | TFLOPs: 62.40 | +[default7]: iteration 1989/ 3814 | consumed samples: 1018368 | consumed tokens: 2085617664 | elapsed time per iteration (s): 6.19 | learning rate: 2.829E-04 | global batch size: 512 | lm loss: 3.480322E+00 | loss scale: 32768.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.648 | TFLOPs: 62.43 | +[default7]: iteration 1990/ 3814 | consumed samples: 1018880 | consumed tokens: 2086666240 | elapsed time per iteration (s): 6.06 | learning rate: 2.827E-04 | global batch size: 512 | lm loss: 3.492766E+00 | loss scale: 32768.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.483 | TFLOPs: 63.81 | +[default7]: iteration 1991/ 3814 | consumed samples: 1019392 | consumed tokens: 2087714816 | elapsed time per iteration (s): 6.02 | learning rate: 2.825E-04 | global batch size: 512 | lm loss: 3.465720E+00 | loss scale: 32768.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.009 | TFLOPs: 64.21 | +[default7]: iteration 1992/ 3814 | consumed samples: 1019904 | consumed tokens: 2088763392 | elapsed time per iteration (s): 6.01 | learning rate: 2.822E-04 | global batch size: 512 | lm loss: 3.521246E+00 | loss scale: 32768.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.260 | TFLOPs: 64.40 | +[default7]: iteration 1993/ 3814 | consumed samples: 1020416 | consumed tokens: 2089811968 | elapsed time per iteration (s): 6.08 | learning rate: 2.820E-04 | global batch size: 512 | lm loss: 3.514592E+00 | loss scale: 32768.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.237 | TFLOPs: 63.63 | +[default7]: iteration 1994/ 3814 | consumed samples: 1020928 | consumed tokens: 2090860544 | elapsed time per iteration (s): 6.15 | learning rate: 2.818E-04 | global batch size: 512 | lm loss: 3.501668E+00 | loss scale: 32768.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.312 | TFLOPs: 62.93 | +[default7]: iteration 1995/ 3814 | consumed samples: 1021440 | consumed tokens: 2091909120 | elapsed time per iteration (s): 6.03 | learning rate: 2.815E-04 | global batch size: 512 | lm loss: 3.467087E+00 | loss scale: 32768.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.970 | TFLOPs: 64.18 | +[default7]: iteration 1996/ 3814 | consumed samples: 1021952 | consumed tokens: 2092957696 | elapsed time per iteration (s): 6.04 | learning rate: 2.813E-04 | global batch size: 512 | lm loss: 3.486448E+00 | loss scale: 32768.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.724 | TFLOPs: 63.99 | +[default7]: iteration 1997/ 3814 | consumed samples: 1022464 | consumed tokens: 2094006272 | elapsed time per iteration (s): 6.01 | learning rate: 2.810E-04 | global batch size: 512 | lm loss: 3.497136E+00 | loss scale: 32768.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.208 | TFLOPs: 64.36 | +[default7]: iteration 1998/ 3814 | consumed samples: 1022976 | consumed tokens: 2095054848 | elapsed time per iteration (s): 6.02 | learning rate: 2.808E-04 | global batch size: 512 | lm loss: 3.510088E+00 | loss scale: 32768.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.999 | TFLOPs: 64.20 | +[default7]: iteration 1999/ 3814 | consumed samples: 1023488 | consumed tokens: 2096103424 | elapsed time per iteration (s): 5.99 | learning rate: 2.806E-04 | global batch size: 512 | lm loss: 3.474784E+00 | loss scale: 32768.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.535 | TFLOPs: 64.61 | +[default7]: iteration 2000/ 3814 | consumed samples: 1024000 | consumed tokens: 2097152000 | elapsed time per iteration (s): 5.95 | learning rate: 2.803E-04 | global batch size: 512 | lm loss: 3.492640E+00 | loss scale: 65536.0 | grad norm: 0.065 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.047 | TFLOPs: 64.99 | +[default0]:[2023-02-16 10:53:03,118] [INFO] [logging.py:68:log_dist] [Rank 0] step=2000, skipped=0, lr=[0.00028033702764557026, 0.00014016851382278513, 0.002803370276455703, 0.00014016851382278513, 0.00028033702764557026, 0.002803370276455703], mom=[(0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95), (0.9, 0.95)] +[default0]:steps: 2000 loss: 3.4926 iter time (s): 5.989 samples/sec: 85.495 +[default7]:------------------------------------------------------------------------------------------ +[default7]:valid loss at iteration 2000 | lm loss value: 3.472962E+00 | lm loss PPL: 3.223207E+01 | +[default7]:------------------------------------------------------------------------------------------ +[default0]:saving checkpoint at iteration 2000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 10:53:04,173] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2000 is begin to save! +[default0]:[2023-02-16 10:53:04,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,341] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,339] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:04,397] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,398] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,401] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:04,458] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,458] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,451] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,451] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:04,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,506] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,514] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,514] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:04,575] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,575] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,560] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,560] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:04,619] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,640] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,640] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,687] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,687] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,698] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:04,758] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,759] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,749] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:04,802] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,803] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,817] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:04,881] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,881] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,857] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,858] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:04,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,916] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:04,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,940] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:04,997] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:04,998] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:04,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:04,973] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,060] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,060] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,035] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,097] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,126] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,126] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:05,185] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,186] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,151] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,152] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,209] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,209] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,245] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,246] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,268] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,268] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,306] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:05,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,325] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,326] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,380] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,425] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,426] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:05,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,488] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,435] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,492] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,493] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,548] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,549] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,619] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,620] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,621] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:05,690] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,691] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,689] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,689] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,748] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,749] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,752] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,752] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,814] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,814] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,814] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:05,883] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,883] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,877] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:05,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:05,942] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:05,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,933] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:05,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:05,991] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:06,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,001] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:06,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:06,048] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:06,049] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:06,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:06,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:06,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,118] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:06,197] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,198] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:06,170] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:06,170] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 10:53:06,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 10:53:06,234] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:06,235] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 10:53:06,235] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 10:53:06,236] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_01_model_states.pt +[default1]:[2023-02-16 10:53:06,237] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 10:53:06,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 10:53:06,307] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 10:53:06,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 10:53:06,309] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_00_model_states.pt +[default0]:[2023-02-16 10:53:06,309] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 10:53:06,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 10:53:06,335] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 10:53:06,795] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:06,795] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:06,795] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:06,824] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:06,824] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:06,824] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:06,821] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:06,822] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:06,822] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,879] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,879] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,880] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:06,861] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:06,861] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:06,861] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:06,894] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:06,894] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:06,894] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,870] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,871] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:06,915] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:06,915] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:06,915] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:06,922] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:06,922] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:06,922] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:06,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:06,864] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:06,864] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:06,886] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:06,887] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:06,887] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:06,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:06,930] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:06,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:06,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:06,895] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:06,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:06,871] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:06,871] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:06,871] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:06,940] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:06,941] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:06,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:06,929] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:06,929] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:06,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:06,930] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:06,930] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:06,930] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:06,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:06,925] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:06,925] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:06,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:06,958] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:06,958] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,945] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,945] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,945] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:06,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:06,940] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:06,940] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:06,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:06,967] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:06,967] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:06,944] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:06,944] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:06,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,970] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,971] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 10:53:06,941] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:06,941] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:06,941] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:06,925] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:06,929] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:06,929] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:06,974] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:06,974] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:06,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,916] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,916] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,916] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,970] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,970] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,970] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:06,943] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:06,944] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:06,944] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:06,939] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:06,939] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:06,939] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 10:53:06,931] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:06,931] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:06,931] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:07,024] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:07,024] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:07,024] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:06,971] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:06,971] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:06,971] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:06,976] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:06,977] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:06,977] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 10:53:06,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:06,949] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:06,949] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:07,038] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:07,038] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:07,038] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:06,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:06,986] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:06,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:06,985] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:06,986] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:06,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:07,025] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:07,025] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:07,025] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:06,973] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:06,974] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:06,974] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:07,031] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:07,031] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:07,031] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:06,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:06,990] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:06,990] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:06,990] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:06,991] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:06,991] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:07,032] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:07,032] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:07,032] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 10:53:07,018] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:07,018] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:07,018] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:07,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:07,085] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:07,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:07,034] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:07,034] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:07,034] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:07,100] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:07,100] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:07,101] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default4]:[2023-02-16 10:53:07,112] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 10:53:07,112] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 10:53:07,112] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:07,110] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:07,110] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:07,110] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 10:53:07,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:07,063] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:07,063] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:07,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:07,061] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:07,061] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:07,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:07,042] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:07,042] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default6]:[2023-02-16 10:53:07,063] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 10:53:07,064] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 10:53:07,064] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:07,053] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:07,053] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:07,053] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default0]:[2023-02-16 10:53:07,090] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 10:53:07,090] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 10:53:07,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:07,058] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:07,058] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:07,058] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default3]:[2023-02-16 10:53:07,091] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 10:53:07,091] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 10:53:07,091] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default1]:[2023-02-16 10:53:07,085] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 10:53:07,085] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 10:53:07,085] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default5]:[2023-02-16 10:53:07,108] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 10:53:07,108] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 10:53:07,108] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default2]:[2023-02-16 10:53:07,088] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 10:53:07,088] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 10:53:07,088] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:time (ms) | save-checkpoint: 2999.06 +[default0]: successfully saved checkpoint at iteration 2000 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:[2023-02-16 10:53:07,144] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:07,144] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:07,144] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]:[2023-02-16 10:53:07,155] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 10:53:07,155] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2000/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 10:53:07,155] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2000 is ready now! +[default7]: iteration 2001/ 3814 | consumed samples: 1024512 | consumed tokens: 2098200576 | elapsed time per iteration (s): 10.23 | learning rate: 2.801E-04 | global batch size: 512 | lm loss: 3.503193E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 50.045 | TFLOPs: 37.80 | +[default7]: iteration 2002/ 3814 | consumed samples: 1025024 | consumed tokens: 2099249152 | elapsed time per iteration (s): 5.94 | learning rate: 2.799E-04 | global batch size: 512 | lm loss: 3.506463E+00 | loss scale: 65536.0 | grad norm: 0.176 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.227 | TFLOPs: 65.13 | +[default7]: iteration 2003/ 3814 | consumed samples: 1025536 | consumed tokens: 2100297728 | elapsed time per iteration (s): 6.00 | learning rate: 2.796E-04 | global batch size: 512 | lm loss: 3.493799E+00 | loss scale: 65536.0 | grad norm: 0.178 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.383 | TFLOPs: 64.49 | +[default7]: iteration 2004/ 3814 | consumed samples: 1026048 | consumed tokens: 2101346304 | elapsed time per iteration (s): 6.23 | learning rate: 2.794E-04 | global batch size: 512 | lm loss: 3.498560E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.239 | TFLOPs: 62.12 | +[default7]: iteration 2005/ 3814 | consumed samples: 1026560 | consumed tokens: 2102394880 | elapsed time per iteration (s): 6.01 | learning rate: 2.792E-04 | global batch size: 512 | lm loss: 3.499252E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.174 | TFLOPs: 64.33 | +[default7]: iteration 2006/ 3814 | consumed samples: 1027072 | consumed tokens: 2103443456 | elapsed time per iteration (s): 6.02 | learning rate: 2.789E-04 | global batch size: 512 | lm loss: 3.486004E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.117 | TFLOPs: 64.29 | +[default7]: iteration 2007/ 3814 | consumed samples: 1027584 | consumed tokens: 2104492032 | elapsed time per iteration (s): 5.99 | learning rate: 2.787E-04 | global batch size: 512 | lm loss: 3.485113E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.410 | TFLOPs: 64.51 | +[default7]: iteration 2008/ 3814 | consumed samples: 1028096 | consumed tokens: 2105540608 | elapsed time per iteration (s): 6.00 | learning rate: 2.785E-04 | global batch size: 512 | lm loss: 3.501492E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.381 | TFLOPs: 64.49 | +[default7]: iteration 2009/ 3814 | consumed samples: 1028608 | consumed tokens: 2106589184 | elapsed time per iteration (s): 6.02 | learning rate: 2.782E-04 | global batch size: 512 | lm loss: 3.477108E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.040 | TFLOPs: 64.23 | +[default7]: iteration 2010/ 3814 | consumed samples: 1029120 | consumed tokens: 2107637760 | elapsed time per iteration (s): 6.20 | learning rate: 2.780E-04 | global batch size: 512 | lm loss: 3.513633E+00 | loss scale: 65536.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.529 | TFLOPs: 62.34 | +[default7]: iteration 2011/ 3814 | consumed samples: 1029632 | consumed tokens: 2108686336 | elapsed time per iteration (s): 5.98 | learning rate: 2.777E-04 | global batch size: 512 | lm loss: 3.521535E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.577 | TFLOPs: 64.64 | +[default7]: iteration 2012/ 3814 | consumed samples: 1030144 | consumed tokens: 2109734912 | elapsed time per iteration (s): 6.20 | learning rate: 2.775E-04 | global batch size: 512 | lm loss: 3.507695E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.596 | TFLOPs: 62.39 | +[default7]: iteration 2013/ 3814 | consumed samples: 1030656 | consumed tokens: 2110783488 | elapsed time per iteration (s): 5.97 | learning rate: 2.773E-04 | global batch size: 512 | lm loss: 3.491759E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.699 | TFLOPs: 64.73 | +[default7]: iteration 2014/ 3814 | consumed samples: 1031168 | consumed tokens: 2111832064 | elapsed time per iteration (s): 6.22 | learning rate: 2.770E-04 | global batch size: 512 | lm loss: 3.502276E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.282 | TFLOPs: 62.15 | +[default7]: iteration 2015/ 3814 | consumed samples: 1031680 | consumed tokens: 2112880640 | elapsed time per iteration (s): 6.14 | learning rate: 2.768E-04 | global batch size: 512 | lm loss: 3.529738E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.404 | TFLOPs: 63.00 | +[default7]: iteration 2016/ 3814 | consumed samples: 1032192 | consumed tokens: 2113929216 | elapsed time per iteration (s): 6.24 | learning rate: 2.766E-04 | global batch size: 512 | lm loss: 3.515925E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.033 | TFLOPs: 61.96 | +[default7]: iteration 2017/ 3814 | consumed samples: 1032704 | consumed tokens: 2114977792 | elapsed time per iteration (s): 6.14 | learning rate: 2.763E-04 | global batch size: 512 | lm loss: 3.516764E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.424 | TFLOPs: 63.01 | +[default7]: iteration 2018/ 3814 | consumed samples: 1033216 | consumed tokens: 2116026368 | elapsed time per iteration (s): 6.19 | learning rate: 2.761E-04 | global batch size: 512 | lm loss: 3.490291E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.708 | TFLOPs: 62.47 | +[default7]: iteration 2019/ 3814 | consumed samples: 1033728 | consumed tokens: 2117074944 | elapsed time per iteration (s): 6.03 | learning rate: 2.759E-04 | global batch size: 512 | lm loss: 3.483834E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.939 | TFLOPs: 64.16 | +[default7]: iteration 2020/ 3814 | consumed samples: 1034240 | consumed tokens: 2118123520 | elapsed time per iteration (s): 6.17 | learning rate: 2.756E-04 | global batch size: 512 | lm loss: 3.468465E+00 | loss scale: 65536.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.995 | TFLOPs: 62.69 | +[default7]: iteration 2021/ 3814 | consumed samples: 1034752 | consumed tokens: 2119172096 | elapsed time per iteration (s): 6.20 | learning rate: 2.754E-04 | global batch size: 512 | lm loss: 3.464908E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.616 | TFLOPs: 62.40 | +[default7]: iteration 2022/ 3814 | consumed samples: 1035264 | consumed tokens: 2120220672 | elapsed time per iteration (s): 6.21 | learning rate: 2.752E-04 | global batch size: 512 | lm loss: 3.508115E+00 | loss scale: 65536.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.401 | TFLOPs: 62.24 | +[default7]: iteration 2023/ 3814 | consumed samples: 1035776 | consumed tokens: 2121269248 | elapsed time per iteration (s): 6.00 | learning rate: 2.749E-04 | global batch size: 512 | lm loss: 3.450940E+00 | loss scale: 65536.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.267 | TFLOPs: 64.40 | +[default7]: iteration 2024/ 3814 | consumed samples: 1036288 | consumed tokens: 2122317824 | elapsed time per iteration (s): 6.01 | learning rate: 2.747E-04 | global batch size: 512 | lm loss: 3.485785E+00 | loss scale: 65536.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.167 | TFLOPs: 64.33 | +[default7]: iteration 2025/ 3814 | consumed samples: 1036800 | consumed tokens: 2123366400 | elapsed time per iteration (s): 6.25 | learning rate: 2.744E-04 | global batch size: 512 | lm loss: 3.504808E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.878 | TFLOPs: 61.84 | +[default7]: iteration 2026/ 3814 | consumed samples: 1037312 | consumed tokens: 2124414976 | elapsed time per iteration (s): 6.07 | learning rate: 2.742E-04 | global batch size: 512 | lm loss: 3.481030E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.348 | TFLOPs: 63.71 | +[default7]: iteration 2027/ 3814 | consumed samples: 1037824 | consumed tokens: 2125463552 | elapsed time per iteration (s): 5.99 | learning rate: 2.740E-04 | global batch size: 512 | lm loss: 3.463514E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.469 | TFLOPs: 64.56 | +[default7]: iteration 2028/ 3814 | consumed samples: 1038336 | consumed tokens: 2126512128 | elapsed time per iteration (s): 5.97 | learning rate: 2.737E-04 | global batch size: 512 | lm loss: 3.531217E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.787 | TFLOPs: 64.80 | +[default7]: iteration 2029/ 3814 | consumed samples: 1038848 | consumed tokens: 2127560704 | elapsed time per iteration (s): 5.94 | learning rate: 2.735E-04 | global batch size: 512 | lm loss: 3.478469E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.205 | TFLOPs: 65.11 | +[default7]: iteration 2030/ 3814 | consumed samples: 1039360 | consumed tokens: 2128609280 | elapsed time per iteration (s): 5.99 | learning rate: 2.733E-04 | global batch size: 512 | lm loss: 3.471544E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.453 | TFLOPs: 64.54 | +[default7]: iteration 2031/ 3814 | consumed samples: 1039872 | consumed tokens: 2129657856 | elapsed time per iteration (s): 5.99 | learning rate: 2.730E-04 | global batch size: 512 | lm loss: 3.477652E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.456 | TFLOPs: 64.55 | +[default7]: iteration 2032/ 3814 | consumed samples: 1040384 | consumed tokens: 2130706432 | elapsed time per iteration (s): 5.91 | learning rate: 2.728E-04 | global batch size: 512 | lm loss: 3.503068E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.642 | TFLOPs: 65.44 | +[default7]: iteration 2033/ 3814 | consumed samples: 1040896 | consumed tokens: 2131755008 | elapsed time per iteration (s): 6.00 | learning rate: 2.726E-04 | global batch size: 512 | lm loss: 3.476691E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.401 | TFLOPs: 64.50 | +[default7]: iteration 2034/ 3814 | consumed samples: 1041408 | consumed tokens: 2132803584 | elapsed time per iteration (s): 5.96 | learning rate: 2.723E-04 | global batch size: 512 | lm loss: 3.469656E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.970 | TFLOPs: 64.93 | +[default7]: iteration 2035/ 3814 | consumed samples: 1041920 | consumed tokens: 2133852160 | elapsed time per iteration (s): 6.00 | learning rate: 2.721E-04 | global batch size: 512 | lm loss: 3.502713E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.362 | TFLOPs: 64.48 | +[default7]: iteration 2036/ 3814 | consumed samples: 1042432 | consumed tokens: 2134900736 | elapsed time per iteration (s): 5.99 | learning rate: 2.718E-04 | global batch size: 512 | lm loss: 3.499487E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.468 | TFLOPs: 64.55 | +[default7]: iteration 2037/ 3814 | consumed samples: 1042944 | consumed tokens: 2135949312 | elapsed time per iteration (s): 5.94 | learning rate: 2.716E-04 | global batch size: 512 | lm loss: 3.489370E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.187 | TFLOPs: 65.10 | +[default7]: iteration 2038/ 3814 | consumed samples: 1043456 | consumed tokens: 2136997888 | elapsed time per iteration (s): 5.98 | learning rate: 2.714E-04 | global batch size: 512 | lm loss: 3.438565E+00 | loss scale: 65536.0 | grad norm: 0.168 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.649 | TFLOPs: 64.69 | +[default7]: iteration 2039/ 3814 | consumed samples: 1043968 | consumed tokens: 2138046464 | elapsed time per iteration (s): 6.04 | learning rate: 2.711E-04 | global batch size: 512 | lm loss: 3.487957E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.821 | TFLOPs: 64.07 | +[default7]: iteration 2040/ 3814 | consumed samples: 1044480 | consumed tokens: 2139095040 | elapsed time per iteration (s): 5.94 | learning rate: 2.709E-04 | global batch size: 512 | lm loss: 3.510892E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.129 | TFLOPs: 65.05 | +[default7]: iteration 2041/ 3814 | consumed samples: 1044992 | consumed tokens: 2140143616 | elapsed time per iteration (s): 6.07 | learning rate: 2.707E-04 | global batch size: 512 | lm loss: 3.481797E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.298 | TFLOPs: 63.67 | +[default7]: iteration 2042/ 3814 | consumed samples: 1045504 | consumed tokens: 2141192192 | elapsed time per iteration (s): 6.02 | learning rate: 2.704E-04 | global batch size: 512 | lm loss: 3.490889E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.062 | TFLOPs: 64.25 | +[default7]: iteration 2043/ 3814 | consumed samples: 1046016 | consumed tokens: 2142240768 | elapsed time per iteration (s): 6.00 | learning rate: 2.702E-04 | global batch size: 512 | lm loss: 3.491556E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.281 | TFLOPs: 64.41 | +[default7]: iteration 2044/ 3814 | consumed samples: 1046528 | consumed tokens: 2143289344 | elapsed time per iteration (s): 6.00 | learning rate: 2.700E-04 | global batch size: 512 | lm loss: 3.476907E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.336 | TFLOPs: 64.46 | +[default7]: iteration 2045/ 3814 | consumed samples: 1047040 | consumed tokens: 2144337920 | elapsed time per iteration (s): 5.95 | learning rate: 2.697E-04 | global batch size: 512 | lm loss: 3.494698E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.039 | TFLOPs: 64.99 | +[default7]: iteration 2046/ 3814 | consumed samples: 1047552 | consumed tokens: 2145386496 | elapsed time per iteration (s): 5.96 | learning rate: 2.695E-04 | global batch size: 512 | lm loss: 3.471966E+00 | loss scale: 65536.0 | grad norm: 0.104 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.872 | TFLOPs: 64.86 | +[default7]: iteration 2047/ 3814 | consumed samples: 1048064 | consumed tokens: 2146435072 | elapsed time per iteration (s): 6.01 | learning rate: 2.693E-04 | global batch size: 512 | lm loss: 3.492777E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.193 | TFLOPs: 64.35 | +[default7]: iteration 2048/ 3814 | consumed samples: 1048576 | consumed tokens: 2147483648 | elapsed time per iteration (s): 5.99 | learning rate: 2.690E-04 | global batch size: 512 | lm loss: 3.490561E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.506 | TFLOPs: 64.58 | +[default7]: iteration 2049/ 3814 | consumed samples: 1049088 | consumed tokens: 2148532224 | elapsed time per iteration (s): 5.98 | learning rate: 2.688E-04 | global batch size: 512 | lm loss: 3.459636E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.658 | TFLOPs: 64.70 | +[default7]: iteration 2050/ 3814 | consumed samples: 1049600 | consumed tokens: 2149580800 | elapsed time per iteration (s): 5.93 | learning rate: 2.685E-04 | global batch size: 512 | lm loss: 3.494579E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.371 | TFLOPs: 65.24 | +[default7]: iteration 2051/ 3814 | consumed samples: 1050112 | consumed tokens: 2150629376 | elapsed time per iteration (s): 5.98 | learning rate: 2.683E-04 | global batch size: 512 | lm loss: 3.479086E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.583 | TFLOPs: 64.64 | +[default7]: iteration 2052/ 3814 | consumed samples: 1050624 | consumed tokens: 2151677952 | elapsed time per iteration (s): 5.92 | learning rate: 2.681E-04 | global batch size: 512 | lm loss: 3.502272E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.491 | TFLOPs: 65.33 | +[default7]: iteration 2053/ 3814 | consumed samples: 1051136 | consumed tokens: 2152726528 | elapsed time per iteration (s): 6.00 | learning rate: 2.678E-04 | global batch size: 512 | lm loss: 3.466484E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.383 | TFLOPs: 64.49 | +[default7]: iteration 2054/ 3814 | consumed samples: 1051648 | consumed tokens: 2153775104 | elapsed time per iteration (s): 5.99 | learning rate: 2.676E-04 | global batch size: 512 | lm loss: 3.473255E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.524 | TFLOPs: 64.60 | +[default7]: iteration 2055/ 3814 | consumed samples: 1052160 | consumed tokens: 2154823680 | elapsed time per iteration (s): 5.94 | learning rate: 2.674E-04 | global batch size: 512 | lm loss: 3.487837E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.263 | TFLOPs: 65.16 | +[default7]: iteration 2056/ 3814 | consumed samples: 1052672 | consumed tokens: 2155872256 | elapsed time per iteration (s): 6.02 | learning rate: 2.671E-04 | global batch size: 512 | lm loss: 3.460787E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.118 | TFLOPs: 64.29 | +[default7]: iteration 2057/ 3814 | consumed samples: 1053184 | consumed tokens: 2156920832 | elapsed time per iteration (s): 6.01 | learning rate: 2.669E-04 | global batch size: 512 | lm loss: 3.482646E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.207 | TFLOPs: 64.36 | +[default7]: iteration 2058/ 3814 | consumed samples: 1053696 | consumed tokens: 2157969408 | elapsed time per iteration (s): 6.00 | learning rate: 2.667E-04 | global batch size: 512 | lm loss: 3.481629E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.306 | TFLOPs: 64.43 | +[default7]: iteration 2059/ 3814 | consumed samples: 1054208 | consumed tokens: 2159017984 | elapsed time per iteration (s): 6.03 | learning rate: 2.664E-04 | global batch size: 512 | lm loss: 3.493011E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.917 | TFLOPs: 64.14 | +[default7]: iteration 2060/ 3814 | consumed samples: 1054720 | consumed tokens: 2160066560 | elapsed time per iteration (s): 5.99 | learning rate: 2.662E-04 | global batch size: 512 | lm loss: 3.504434E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.494 | TFLOPs: 64.57 | +[default7]: iteration 2061/ 3814 | consumed samples: 1055232 | consumed tokens: 2161115136 | elapsed time per iteration (s): 6.02 | learning rate: 2.659E-04 | global batch size: 512 | lm loss: 3.450832E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.092 | TFLOPs: 64.27 | +[default7]: iteration 2062/ 3814 | consumed samples: 1055744 | consumed tokens: 2162163712 | elapsed time per iteration (s): 6.00 | learning rate: 2.657E-04 | global batch size: 512 | lm loss: 3.435181E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.333 | TFLOPs: 64.45 | +[default7]: iteration 2063/ 3814 | consumed samples: 1056256 | consumed tokens: 2163212288 | elapsed time per iteration (s): 5.94 | learning rate: 2.655E-04 | global batch size: 512 | lm loss: 3.461947E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.250 | TFLOPs: 65.15 | +[default7]: iteration 2064/ 3814 | consumed samples: 1056768 | consumed tokens: 2164260864 | elapsed time per iteration (s): 5.98 | learning rate: 2.652E-04 | global batch size: 512 | lm loss: 3.480065E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.670 | TFLOPs: 64.71 | +[default7]: iteration 2065/ 3814 | consumed samples: 1057280 | consumed tokens: 2165309440 | elapsed time per iteration (s): 5.97 | learning rate: 2.650E-04 | global batch size: 512 | lm loss: 3.469322E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.708 | TFLOPs: 64.74 | +[default7]: iteration 2066/ 3814 | consumed samples: 1057792 | consumed tokens: 2166358016 | elapsed time per iteration (s): 6.04 | learning rate: 2.648E-04 | global batch size: 512 | lm loss: 3.483568E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.722 | TFLOPs: 63.99 | +[default7]: iteration 2067/ 3814 | consumed samples: 1058304 | consumed tokens: 2167406592 | elapsed time per iteration (s): 5.99 | learning rate: 2.645E-04 | global batch size: 512 | lm loss: 3.480366E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.541 | TFLOPs: 64.61 | +[default7]: iteration 2068/ 3814 | consumed samples: 1058816 | consumed tokens: 2168455168 | elapsed time per iteration (s): 6.01 | learning rate: 2.643E-04 | global batch size: 512 | lm loss: 3.463224E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.134 | TFLOPs: 64.30 | +[default7]: iteration 2069/ 3814 | consumed samples: 1059328 | consumed tokens: 2169503744 | elapsed time per iteration (s): 5.99 | learning rate: 2.641E-04 | global batch size: 512 | lm loss: 3.471555E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.441 | TFLOPs: 64.53 | +[default7]: iteration 2070/ 3814 | consumed samples: 1059840 | consumed tokens: 2170552320 | elapsed time per iteration (s): 6.06 | learning rate: 2.638E-04 | global batch size: 512 | lm loss: 3.466952E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.541 | TFLOPs: 63.85 | +[default7]: iteration 2071/ 3814 | consumed samples: 1060352 | consumed tokens: 2171600896 | elapsed time per iteration (s): 5.99 | learning rate: 2.636E-04 | global batch size: 512 | lm loss: 3.501410E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.535 | TFLOPs: 64.61 | +[default7]: iteration 2072/ 3814 | consumed samples: 1060864 | consumed tokens: 2172649472 | elapsed time per iteration (s): 5.97 | learning rate: 2.633E-04 | global batch size: 512 | lm loss: 3.468466E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.727 | TFLOPs: 64.75 | +[default7]: iteration 2073/ 3814 | consumed samples: 1061376 | consumed tokens: 2173698048 | elapsed time per iteration (s): 6.00 | learning rate: 2.631E-04 | global batch size: 512 | lm loss: 3.506580E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 2074/ 3814 | consumed samples: 1061888 | consumed tokens: 2174746624 | elapsed time per iteration (s): 6.00 | learning rate: 2.629E-04 | global batch size: 512 | lm loss: 3.498472E+00 | loss scale: 65536.0 | grad norm: 0.158 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.399 | TFLOPs: 64.50 | +[default7]: iteration 2075/ 3814 | consumed samples: 1062400 | consumed tokens: 2175795200 | elapsed time per iteration (s): 6.02 | learning rate: 2.626E-04 | global batch size: 512 | lm loss: 3.493738E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.025 | TFLOPs: 64.22 | +[default7]: iteration 2076/ 3814 | consumed samples: 1062912 | consumed tokens: 2176843776 | elapsed time per iteration (s): 5.94 | learning rate: 2.624E-04 | global batch size: 512 | lm loss: 3.458840E+00 | loss scale: 65536.0 | grad norm: 0.180 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.154 | TFLOPs: 65.07 | +[default7]: iteration 2077/ 3814 | consumed samples: 1063424 | consumed tokens: 2177892352 | elapsed time per iteration (s): 5.99 | learning rate: 2.622E-04 | global batch size: 512 | lm loss: 3.484365E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.501 | TFLOPs: 64.58 | +[default7]: iteration 2078/ 3814 | consumed samples: 1063936 | consumed tokens: 2178940928 | elapsed time per iteration (s): 6.03 | learning rate: 2.619E-04 | global batch size: 512 | lm loss: 3.439188E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.978 | TFLOPs: 64.18 | +[default7]: iteration 2079/ 3814 | consumed samples: 1064448 | consumed tokens: 2179989504 | elapsed time per iteration (s): 6.06 | learning rate: 2.617E-04 | global batch size: 512 | lm loss: 3.501447E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.444 | TFLOPs: 63.78 | +[default7]: iteration 2080/ 3814 | consumed samples: 1064960 | consumed tokens: 2181038080 | elapsed time per iteration (s): 5.92 | learning rate: 2.615E-04 | global batch size: 512 | lm loss: 3.502321E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.558 | TFLOPs: 65.38 | +[default7]: iteration 2081/ 3814 | consumed samples: 1065472 | consumed tokens: 2182086656 | elapsed time per iteration (s): 6.04 | learning rate: 2.612E-04 | global batch size: 512 | lm loss: 3.438519E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.811 | TFLOPs: 64.06 | +[default7]: iteration 2082/ 3814 | consumed samples: 1065984 | consumed tokens: 2183135232 | elapsed time per iteration (s): 6.00 | learning rate: 2.610E-04 | global batch size: 512 | lm loss: 3.470574E+00 | loss scale: 65536.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.350 | TFLOPs: 64.47 | +[default7]: iteration 2083/ 3814 | consumed samples: 1066496 | consumed tokens: 2184183808 | elapsed time per iteration (s): 6.01 | learning rate: 2.607E-04 | global batch size: 512 | lm loss: 3.444382E+00 | loss scale: 65536.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.172 | TFLOPs: 64.33 | +[default7]: iteration 2084/ 3814 | consumed samples: 1067008 | consumed tokens: 2185232384 | elapsed time per iteration (s): 5.99 | learning rate: 2.605E-04 | global batch size: 512 | lm loss: 3.444921E+00 | loss scale: 65536.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.489 | TFLOPs: 64.57 | +[default7]: iteration 2085/ 3814 | consumed samples: 1067520 | consumed tokens: 2186280960 | elapsed time per iteration (s): 5.99 | learning rate: 2.603E-04 | global batch size: 512 | lm loss: 3.470917E+00 | loss scale: 65536.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.464 | TFLOPs: 64.55 | +[default7]: iteration 2086/ 3814 | consumed samples: 1068032 | consumed tokens: 2187329536 | elapsed time per iteration (s): 6.00 | learning rate: 2.600E-04 | global batch size: 512 | lm loss: 3.455020E+00 | loss scale: 65536.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.362 | TFLOPs: 64.47 | +[default7]: iteration 2087/ 3814 | consumed samples: 1068544 | consumed tokens: 2188378112 | elapsed time per iteration (s): 5.99 | learning rate: 2.598E-04 | global batch size: 512 | lm loss: 3.476300E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.470 | TFLOPs: 64.56 | +[default7]: iteration 2088/ 3814 | consumed samples: 1069056 | consumed tokens: 2189426688 | elapsed time per iteration (s): 5.99 | learning rate: 2.596E-04 | global batch size: 512 | lm loss: 3.462677E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.537 | TFLOPs: 64.61 | +[default7]: iteration 2089/ 3814 | consumed samples: 1069568 | consumed tokens: 2190475264 | elapsed time per iteration (s): 6.00 | learning rate: 2.593E-04 | global batch size: 512 | lm loss: 3.466965E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.293 | TFLOPs: 64.42 | +[default7]: iteration 2090/ 3814 | consumed samples: 1070080 | consumed tokens: 2191523840 | elapsed time per iteration (s): 5.95 | learning rate: 2.591E-04 | global batch size: 512 | lm loss: 3.471966E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.983 | TFLOPs: 64.94 | +[default7]: iteration 2091/ 3814 | consumed samples: 1070592 | consumed tokens: 2192572416 | elapsed time per iteration (s): 5.97 | learning rate: 2.589E-04 | global batch size: 512 | lm loss: 3.469473E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.698 | TFLOPs: 64.73 | +[default7]: iteration 2092/ 3814 | consumed samples: 1071104 | consumed tokens: 2193620992 | elapsed time per iteration (s): 5.99 | learning rate: 2.586E-04 | global batch size: 512 | lm loss: 3.461052E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.469 | TFLOPs: 64.56 | +[default7]: iteration 2093/ 3814 | consumed samples: 1071616 | consumed tokens: 2194669568 | elapsed time per iteration (s): 6.00 | learning rate: 2.584E-04 | global batch size: 512 | lm loss: 3.448733E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 2094/ 3814 | consumed samples: 1072128 | consumed tokens: 2195718144 | elapsed time per iteration (s): 5.98 | learning rate: 2.581E-04 | global batch size: 512 | lm loss: 3.486324E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.674 | TFLOPs: 64.71 | +[default7]: iteration 2095/ 3814 | consumed samples: 1072640 | consumed tokens: 2196766720 | elapsed time per iteration (s): 5.96 | learning rate: 2.579E-04 | global batch size: 512 | lm loss: 3.437427E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.886 | TFLOPs: 64.87 | +[default7]: iteration 2096/ 3814 | consumed samples: 1073152 | consumed tokens: 2197815296 | elapsed time per iteration (s): 6.02 | learning rate: 2.577E-04 | global batch size: 512 | lm loss: 3.440246E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.079 | TFLOPs: 64.26 | +[default7]: iteration 2097/ 3814 | consumed samples: 1073664 | consumed tokens: 2198863872 | elapsed time per iteration (s): 5.99 | learning rate: 2.574E-04 | global batch size: 512 | lm loss: 3.486644E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.504 | TFLOPs: 64.58 | +[default7]: iteration 2098/ 3814 | consumed samples: 1074176 | consumed tokens: 2199912448 | elapsed time per iteration (s): 5.83 | learning rate: 2.572E-04 | global batch size: 512 | lm loss: 3.464460E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.748 | TFLOPs: 66.28 | +[default7]: iteration 2099/ 3814 | consumed samples: 1074688 | consumed tokens: 2200961024 | elapsed time per iteration (s): 5.98 | learning rate: 2.570E-04 | global batch size: 512 | lm loss: 3.424252E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.637 | TFLOPs: 64.68 | +[default7]: iteration 2100/ 3814 | consumed samples: 1075200 | consumed tokens: 2202009600 | elapsed time per iteration (s): 5.93 | learning rate: 2.567E-04 | global batch size: 512 | lm loss: 3.444355E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.369 | TFLOPs: 65.24 | +[default7]: iteration 2101/ 3814 | consumed samples: 1075712 | consumed tokens: 2203058176 | elapsed time per iteration (s): 6.02 | learning rate: 2.565E-04 | global batch size: 512 | lm loss: 3.482756E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.030 | TFLOPs: 64.22 | +[default7]: iteration 2102/ 3814 | consumed samples: 1076224 | consumed tokens: 2204106752 | elapsed time per iteration (s): 6.05 | learning rate: 2.563E-04 | global batch size: 512 | lm loss: 3.474735E+00 | loss scale: 65536.0 | grad norm: 0.151 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.610 | TFLOPs: 63.91 | +[default7]: iteration 2103/ 3814 | consumed samples: 1076736 | consumed tokens: 2205155328 | elapsed time per iteration (s): 5.99 | learning rate: 2.560E-04 | global batch size: 512 | lm loss: 3.468875E+00 | loss scale: 65536.0 | grad norm: 0.150 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.412 | TFLOPs: 64.51 | +[default7]: iteration 2104/ 3814 | consumed samples: 1077248 | consumed tokens: 2206203904 | elapsed time per iteration (s): 6.02 | learning rate: 2.558E-04 | global batch size: 512 | lm loss: 3.459788E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.007 | TFLOPs: 64.21 | +[default7]: iteration 2105/ 3814 | consumed samples: 1077760 | consumed tokens: 2207252480 | elapsed time per iteration (s): 6.02 | learning rate: 2.555E-04 | global batch size: 512 | lm loss: 3.443131E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.056 | TFLOPs: 64.24 | +[default7]: iteration 2106/ 3814 | consumed samples: 1078272 | consumed tokens: 2208301056 | elapsed time per iteration (s): 6.03 | learning rate: 2.553E-04 | global batch size: 512 | lm loss: 3.477222E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.848 | TFLOPs: 64.09 | +[default7]: iteration 2107/ 3814 | consumed samples: 1078784 | consumed tokens: 2209349632 | elapsed time per iteration (s): 5.99 | learning rate: 2.551E-04 | global batch size: 512 | lm loss: 3.476046E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.457 | TFLOPs: 64.55 | +[default7]: iteration 2108/ 3814 | consumed samples: 1079296 | consumed tokens: 2210398208 | elapsed time per iteration (s): 5.99 | learning rate: 2.548E-04 | global batch size: 512 | lm loss: 3.449657E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.500 | TFLOPs: 64.58 | +[default7]: iteration 2109/ 3814 | consumed samples: 1079808 | consumed tokens: 2211446784 | elapsed time per iteration (s): 6.04 | learning rate: 2.546E-04 | global batch size: 512 | lm loss: 3.473989E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.791 | TFLOPs: 64.04 | +[default7]: iteration 2110/ 3814 | consumed samples: 1080320 | consumed tokens: 2212495360 | elapsed time per iteration (s): 6.00 | learning rate: 2.544E-04 | global batch size: 512 | lm loss: 3.449737E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.333 | TFLOPs: 64.45 | +[default7]: iteration 2111/ 3814 | consumed samples: 1080832 | consumed tokens: 2213543936 | elapsed time per iteration (s): 6.03 | learning rate: 2.541E-04 | global batch size: 512 | lm loss: 3.463064E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.949 | TFLOPs: 64.16 | +[default7]: iteration 2112/ 3814 | consumed samples: 1081344 | consumed tokens: 2214592512 | elapsed time per iteration (s): 6.03 | learning rate: 2.539E-04 | global batch size: 512 | lm loss: 3.445074E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.905 | TFLOPs: 64.13 | +[default7]: iteration 2113/ 3814 | consumed samples: 1081856 | consumed tokens: 2215641088 | elapsed time per iteration (s): 6.02 | learning rate: 2.537E-04 | global batch size: 512 | lm loss: 3.459148E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.090 | TFLOPs: 64.27 | +[default7]: iteration 2114/ 3814 | consumed samples: 1082368 | consumed tokens: 2216689664 | elapsed time per iteration (s): 5.90 | learning rate: 2.534E-04 | global batch size: 512 | lm loss: 3.469102E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.744 | TFLOPs: 65.52 | +[default7]: iteration 2115/ 3814 | consumed samples: 1082880 | consumed tokens: 2217738240 | elapsed time per iteration (s): 6.03 | learning rate: 2.532E-04 | global batch size: 512 | lm loss: 3.483449E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.965 | TFLOPs: 64.18 | +[default7]: iteration 2116/ 3814 | consumed samples: 1083392 | consumed tokens: 2218786816 | elapsed time per iteration (s): 6.01 | learning rate: 2.530E-04 | global batch size: 512 | lm loss: 3.466304E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.160 | TFLOPs: 64.32 | +[default7]: iteration 2117/ 3814 | consumed samples: 1083904 | consumed tokens: 2219835392 | elapsed time per iteration (s): 6.01 | learning rate: 2.527E-04 | global batch size: 512 | lm loss: 3.437682E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.131 | TFLOPs: 64.30 | +[default7]: iteration 2118/ 3814 | consumed samples: 1084416 | consumed tokens: 2220883968 | elapsed time per iteration (s): 6.00 | learning rate: 2.525E-04 | global batch size: 512 | lm loss: 3.457849E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.318 | TFLOPs: 64.44 | +[default7]: iteration 2119/ 3814 | consumed samples: 1084928 | consumed tokens: 2221932544 | elapsed time per iteration (s): 5.96 | learning rate: 2.522E-04 | global batch size: 512 | lm loss: 3.479664E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.858 | TFLOPs: 64.85 | +[default7]: iteration 2120/ 3814 | consumed samples: 1085440 | consumed tokens: 2222981120 | elapsed time per iteration (s): 6.04 | learning rate: 2.520E-04 | global batch size: 512 | lm loss: 3.439787E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.704 | TFLOPs: 63.98 | +[default7]: iteration 2121/ 3814 | consumed samples: 1085952 | consumed tokens: 2224029696 | elapsed time per iteration (s): 5.93 | learning rate: 2.518E-04 | global batch size: 512 | lm loss: 3.437575E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.332 | TFLOPs: 65.21 | +[default7]: iteration 2122/ 3814 | consumed samples: 1086464 | consumed tokens: 2225078272 | elapsed time per iteration (s): 6.05 | learning rate: 2.515E-04 | global batch size: 512 | lm loss: 3.428245E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.641 | TFLOPs: 63.93 | +[default7]: iteration 2123/ 3814 | consumed samples: 1086976 | consumed tokens: 2226126848 | elapsed time per iteration (s): 5.97 | learning rate: 2.513E-04 | global batch size: 512 | lm loss: 3.459948E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.719 | TFLOPs: 64.74 | +[default7]: iteration 2124/ 3814 | consumed samples: 1087488 | consumed tokens: 2227175424 | elapsed time per iteration (s): 6.02 | learning rate: 2.511E-04 | global batch size: 512 | lm loss: 3.455604E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.018 | TFLOPs: 64.22 | +[default7]: iteration 2125/ 3814 | consumed samples: 1088000 | consumed tokens: 2228224000 | elapsed time per iteration (s): 6.04 | learning rate: 2.508E-04 | global batch size: 512 | lm loss: 3.464376E+00 | loss scale: 65536.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.817 | TFLOPs: 64.06 | +[default7]: iteration 2126/ 3814 | consumed samples: 1088512 | consumed tokens: 2229272576 | elapsed time per iteration (s): 6.03 | learning rate: 2.506E-04 | global batch size: 512 | lm loss: 3.449735E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.881 | TFLOPs: 64.11 | +[default7]: iteration 2127/ 3814 | consumed samples: 1089024 | consumed tokens: 2230321152 | elapsed time per iteration (s): 5.87 | learning rate: 2.504E-04 | global batch size: 512 | lm loss: 3.455798E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.167 | TFLOPs: 65.84 | +[default7]: iteration 2128/ 3814 | consumed samples: 1089536 | consumed tokens: 2231369728 | elapsed time per iteration (s): 5.99 | learning rate: 2.501E-04 | global batch size: 512 | lm loss: 3.455035E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.492 | TFLOPs: 64.57 | +[default7]: iteration 2129/ 3814 | consumed samples: 1090048 | consumed tokens: 2232418304 | elapsed time per iteration (s): 5.98 | learning rate: 2.499E-04 | global batch size: 512 | lm loss: 3.448483E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.650 | TFLOPs: 64.69 | +[default7]: iteration 2130/ 3814 | consumed samples: 1090560 | consumed tokens: 2233466880 | elapsed time per iteration (s): 5.99 | learning rate: 2.496E-04 | global batch size: 512 | lm loss: 3.422462E+00 | loss scale: 65536.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.446 | TFLOPs: 64.54 | +[default7]: iteration 2131/ 3814 | consumed samples: 1091072 | consumed tokens: 2234515456 | elapsed time per iteration (s): 6.00 | learning rate: 2.494E-04 | global batch size: 512 | lm loss: 3.470043E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.314 | TFLOPs: 64.44 | +[default7]: iteration 2132/ 3814 | consumed samples: 1091584 | consumed tokens: 2235564032 | elapsed time per iteration (s): 6.01 | learning rate: 2.492E-04 | global batch size: 512 | lm loss: 3.464213E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.125 | TFLOPs: 64.30 | +[default7]: iteration 2133/ 3814 | consumed samples: 1092096 | consumed tokens: 2236612608 | elapsed time per iteration (s): 6.00 | learning rate: 2.489E-04 | global batch size: 512 | lm loss: 3.468959E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.402 | TFLOPs: 64.51 | +[default7]: iteration 2134/ 3814 | consumed samples: 1092608 | consumed tokens: 2237661184 | elapsed time per iteration (s): 5.97 | learning rate: 2.487E-04 | global batch size: 512 | lm loss: 3.447730E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.754 | TFLOPs: 64.77 | +[default7]: iteration 2135/ 3814 | consumed samples: 1093120 | consumed tokens: 2238709760 | elapsed time per iteration (s): 5.91 | learning rate: 2.485E-04 | global batch size: 512 | lm loss: 3.441082E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.615 | TFLOPs: 65.42 | +[default7]: iteration 2136/ 3814 | consumed samples: 1093632 | consumed tokens: 2239758336 | elapsed time per iteration (s): 5.91 | learning rate: 2.482E-04 | global batch size: 512 | lm loss: 3.446120E+00 | loss scale: 65536.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.562 | TFLOPs: 65.38 | +[default7]: iteration 2137/ 3814 | consumed samples: 1094144 | consumed tokens: 2240806912 | elapsed time per iteration (s): 6.02 | learning rate: 2.480E-04 | global batch size: 512 | lm loss: 3.471034E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.982 | TFLOPs: 64.19 | +[default7]: iteration 2138/ 3814 | consumed samples: 1094656 | consumed tokens: 2241855488 | elapsed time per iteration (s): 5.92 | learning rate: 2.478E-04 | global batch size: 512 | lm loss: 3.459351E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.454 | TFLOPs: 65.30 | +[default7]: iteration 2139/ 3814 | consumed samples: 1095168 | consumed tokens: 2242904064 | elapsed time per iteration (s): 5.93 | learning rate: 2.475E-04 | global batch size: 512 | lm loss: 3.427016E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.412 | TFLOPs: 65.27 | +[default7]: iteration 2140/ 3814 | consumed samples: 1095680 | consumed tokens: 2243952640 | elapsed time per iteration (s): 5.97 | learning rate: 2.473E-04 | global batch size: 512 | lm loss: 3.432652E+00 | loss scale: 65536.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.764 | TFLOPs: 64.78 | +[default7]: iteration 2141/ 3814 | consumed samples: 1096192 | consumed tokens: 2245001216 | elapsed time per iteration (s): 5.93 | learning rate: 2.470E-04 | global batch size: 512 | lm loss: 3.438768E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.393 | TFLOPs: 65.25 | +[default7]: iteration 2142/ 3814 | consumed samples: 1096704 | consumed tokens: 2246049792 | elapsed time per iteration (s): 5.99 | learning rate: 2.468E-04 | global batch size: 512 | lm loss: 3.451389E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.541 | TFLOPs: 64.61 | +[default7]: iteration 2143/ 3814 | consumed samples: 1097216 | consumed tokens: 2247098368 | elapsed time per iteration (s): 6.01 | learning rate: 2.466E-04 | global batch size: 512 | lm loss: 3.450778E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.251 | TFLOPs: 64.39 | +[default7]: iteration 2144/ 3814 | consumed samples: 1097728 | consumed tokens: 2248146944 | elapsed time per iteration (s): 6.03 | learning rate: 2.463E-04 | global batch size: 512 | lm loss: 3.446017E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.979 | TFLOPs: 64.19 | +[default7]: iteration 2145/ 3814 | consumed samples: 1098240 | consumed tokens: 2249195520 | elapsed time per iteration (s): 5.96 | learning rate: 2.461E-04 | global batch size: 512 | lm loss: 3.445961E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.843 | TFLOPs: 64.84 | +[default7]: iteration 2146/ 3814 | consumed samples: 1098752 | consumed tokens: 2250244096 | elapsed time per iteration (s): 5.99 | learning rate: 2.459E-04 | global batch size: 512 | lm loss: 3.455186E+00 | loss scale: 65536.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.488 | TFLOPs: 64.57 | +[default7]: iteration 2147/ 3814 | consumed samples: 1099264 | consumed tokens: 2251292672 | elapsed time per iteration (s): 6.04 | learning rate: 2.456E-04 | global batch size: 512 | lm loss: 3.447179E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.802 | TFLOPs: 64.05 | +[default7]: iteration 2148/ 3814 | consumed samples: 1099776 | consumed tokens: 2252341248 | elapsed time per iteration (s): 5.95 | learning rate: 2.454E-04 | global batch size: 512 | lm loss: 3.452761E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.097 | TFLOPs: 65.03 | +[default7]: iteration 2149/ 3814 | consumed samples: 1100288 | consumed tokens: 2253389824 | elapsed time per iteration (s): 5.99 | learning rate: 2.452E-04 | global batch size: 512 | lm loss: 3.417772E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.498 | TFLOPs: 64.58 | +[default7]: iteration 2150/ 3814 | consumed samples: 1100800 | consumed tokens: 2254438400 | elapsed time per iteration (s): 5.96 | learning rate: 2.449E-04 | global batch size: 512 | lm loss: 3.459816E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.959 | TFLOPs: 64.93 | +[default7]: iteration 2151/ 3814 | consumed samples: 1101312 | consumed tokens: 2255486976 | elapsed time per iteration (s): 6.03 | learning rate: 2.447E-04 | global batch size: 512 | lm loss: 3.449394E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.953 | TFLOPs: 64.17 | +[default7]: iteration 2152/ 3814 | consumed samples: 1101824 | consumed tokens: 2256535552 | elapsed time per iteration (s): 5.91 | learning rate: 2.445E-04 | global batch size: 512 | lm loss: 3.440054E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.579 | TFLOPs: 65.39 | +[default7]: iteration 2153/ 3814 | consumed samples: 1102336 | consumed tokens: 2257584128 | elapsed time per iteration (s): 5.99 | learning rate: 2.442E-04 | global batch size: 512 | lm loss: 3.436426E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.456 | TFLOPs: 64.55 | +[default7]: iteration 2154/ 3814 | consumed samples: 1102848 | consumed tokens: 2258632704 | elapsed time per iteration (s): 5.97 | learning rate: 2.440E-04 | global batch size: 512 | lm loss: 3.446681E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.767 | TFLOPs: 64.78 | +[default7]: iteration 2155/ 3814 | consumed samples: 1103360 | consumed tokens: 2259681280 | elapsed time per iteration (s): 5.93 | learning rate: 2.437E-04 | global batch size: 512 | lm loss: 3.446157E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.407 | TFLOPs: 65.26 | +[default7]: iteration 2156/ 3814 | consumed samples: 1103872 | consumed tokens: 2260729856 | elapsed time per iteration (s): 6.04 | learning rate: 2.435E-04 | global batch size: 512 | lm loss: 3.470140E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.743 | TFLOPs: 64.01 | +[default7]: iteration 2157/ 3814 | consumed samples: 1104384 | consumed tokens: 2261778432 | elapsed time per iteration (s): 6.00 | learning rate: 2.433E-04 | global batch size: 512 | lm loss: 3.449538E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.267 | TFLOPs: 64.40 | +[default7]: iteration 2158/ 3814 | consumed samples: 1104896 | consumed tokens: 2262827008 | elapsed time per iteration (s): 6.03 | learning rate: 2.430E-04 | global batch size: 512 | lm loss: 3.447774E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.878 | TFLOPs: 64.11 | +[default7]: iteration 2159/ 3814 | consumed samples: 1105408 | consumed tokens: 2263875584 | elapsed time per iteration (s): 6.01 | learning rate: 2.428E-04 | global batch size: 512 | lm loss: 3.436077E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.253 | TFLOPs: 64.39 | +[default7]: iteration 2160/ 3814 | consumed samples: 1105920 | consumed tokens: 2264924160 | elapsed time per iteration (s): 5.96 | learning rate: 2.426E-04 | global batch size: 512 | lm loss: 3.444345E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.867 | TFLOPs: 64.86 | +[default7]: iteration 2161/ 3814 | consumed samples: 1106432 | consumed tokens: 2265972736 | elapsed time per iteration (s): 5.91 | learning rate: 2.423E-04 | global batch size: 512 | lm loss: 3.447260E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.594 | TFLOPs: 65.41 | +[default7]: iteration 2162/ 3814 | consumed samples: 1106944 | consumed tokens: 2267021312 | elapsed time per iteration (s): 6.01 | learning rate: 2.421E-04 | global batch size: 512 | lm loss: 3.432751E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.211 | TFLOPs: 64.36 | +[default7]: iteration 2163/ 3814 | consumed samples: 1107456 | consumed tokens: 2268069888 | elapsed time per iteration (s): 5.96 | learning rate: 2.419E-04 | global batch size: 512 | lm loss: 3.463034E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.927 | TFLOPs: 64.90 | +[default7]: iteration 2164/ 3814 | consumed samples: 1107968 | consumed tokens: 2269118464 | elapsed time per iteration (s): 6.01 | learning rate: 2.416E-04 | global batch size: 512 | lm loss: 3.435791E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.199 | TFLOPs: 64.35 | +[default7]: iteration 2165/ 3814 | consumed samples: 1108480 | consumed tokens: 2270167040 | elapsed time per iteration (s): 5.97 | learning rate: 2.414E-04 | global batch size: 512 | lm loss: 3.459863E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.806 | TFLOPs: 64.81 | +[default7]: iteration 2166/ 3814 | consumed samples: 1108992 | consumed tokens: 2271215616 | elapsed time per iteration (s): 5.93 | learning rate: 2.412E-04 | global batch size: 512 | lm loss: 3.432161E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.307 | TFLOPs: 65.19 | +[default7]: iteration 2167/ 3814 | consumed samples: 1109504 | consumed tokens: 2272264192 | elapsed time per iteration (s): 6.01 | learning rate: 2.409E-04 | global batch size: 512 | lm loss: 3.439249E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.216 | TFLOPs: 64.36 | +[default7]: iteration 2168/ 3814 | consumed samples: 1110016 | consumed tokens: 2273312768 | elapsed time per iteration (s): 5.90 | learning rate: 2.407E-04 | global batch size: 512 | lm loss: 3.410022E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.811 | TFLOPs: 65.57 | +[default7]: iteration 2169/ 3814 | consumed samples: 1110528 | consumed tokens: 2274361344 | elapsed time per iteration (s): 5.93 | learning rate: 2.404E-04 | global batch size: 512 | lm loss: 3.439427E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.367 | TFLOPs: 65.23 | +[default7]: iteration 2170/ 3814 | consumed samples: 1111040 | consumed tokens: 2275409920 | elapsed time per iteration (s): 6.02 | learning rate: 2.402E-04 | global batch size: 512 | lm loss: 3.416492E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.038 | TFLOPs: 64.23 | +[default7]: iteration 2171/ 3814 | consumed samples: 1111552 | consumed tokens: 2276458496 | elapsed time per iteration (s): 6.04 | learning rate: 2.400E-04 | global batch size: 512 | lm loss: 3.434164E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.791 | TFLOPs: 64.04 | +[default7]: iteration 2172/ 3814 | consumed samples: 1112064 | consumed tokens: 2277507072 | elapsed time per iteration (s): 6.14 | learning rate: 2.397E-04 | global batch size: 512 | lm loss: 3.409380E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.361 | TFLOPs: 62.96 | +[default7]: iteration 2173/ 3814 | consumed samples: 1112576 | consumed tokens: 2278555648 | elapsed time per iteration (s): 6.08 | learning rate: 2.395E-04 | global batch size: 512 | lm loss: 3.454082E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.253 | TFLOPs: 63.64 | +[default7]: iteration 2174/ 3814 | consumed samples: 1113088 | consumed tokens: 2279604224 | elapsed time per iteration (s): 6.13 | learning rate: 2.393E-04 | global batch size: 512 | lm loss: 3.457376E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.544 | TFLOPs: 63.10 | +[default7]: iteration 2175/ 3814 | consumed samples: 1113600 | consumed tokens: 2280652800 | elapsed time per iteration (s): 6.12 | learning rate: 2.390E-04 | global batch size: 512 | lm loss: 3.438307E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.637 | TFLOPs: 63.17 | +[default7]: iteration 2176/ 3814 | consumed samples: 1114112 | consumed tokens: 2281701376 | elapsed time per iteration (s): 6.16 | learning rate: 2.388E-04 | global batch size: 512 | lm loss: 3.415725E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.095 | TFLOPs: 62.76 | +[default7]: iteration 2177/ 3814 | consumed samples: 1114624 | consumed tokens: 2282749952 | elapsed time per iteration (s): 6.01 | learning rate: 2.386E-04 | global batch size: 512 | lm loss: 3.454112E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.144 | TFLOPs: 64.31 | +[default7]: iteration 2178/ 3814 | consumed samples: 1115136 | consumed tokens: 2283798528 | elapsed time per iteration (s): 6.11 | learning rate: 2.383E-04 | global batch size: 512 | lm loss: 3.476297E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.750 | TFLOPs: 63.26 | +[default7]: iteration 2179/ 3814 | consumed samples: 1115648 | consumed tokens: 2284847104 | elapsed time per iteration (s): 6.00 | learning rate: 2.381E-04 | global batch size: 512 | lm loss: 3.445450E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.270 | TFLOPs: 64.41 | +[default7]: iteration 2180/ 3814 | consumed samples: 1116160 | consumed tokens: 2285895680 | elapsed time per iteration (s): 5.98 | learning rate: 2.379E-04 | global batch size: 512 | lm loss: 3.436956E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.631 | TFLOPs: 64.68 | +[default7]: iteration 2181/ 3814 | consumed samples: 1116672 | consumed tokens: 2286944256 | elapsed time per iteration (s): 6.06 | learning rate: 2.376E-04 | global batch size: 512 | lm loss: 3.446600E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.457 | TFLOPs: 63.79 | +[default7]: iteration 2182/ 3814 | consumed samples: 1117184 | consumed tokens: 2287992832 | elapsed time per iteration (s): 6.21 | learning rate: 2.374E-04 | global batch size: 512 | lm loss: 3.427378E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.487 | TFLOPs: 62.30 | +[default7]: iteration 2183/ 3814 | consumed samples: 1117696 | consumed tokens: 2289041408 | elapsed time per iteration (s): 6.12 | learning rate: 2.371E-04 | global batch size: 512 | lm loss: 3.416306E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.630 | TFLOPs: 63.17 | +[default7]: iteration 2184/ 3814 | consumed samples: 1118208 | consumed tokens: 2290089984 | elapsed time per iteration (s): 6.11 | learning rate: 2.369E-04 | global batch size: 512 | lm loss: 3.456946E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.815 | TFLOPs: 63.31 | +[default7]: iteration 2185/ 3814 | consumed samples: 1118720 | consumed tokens: 2291138560 | elapsed time per iteration (s): 6.19 | learning rate: 2.367E-04 | global batch size: 512 | lm loss: 3.434621E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.660 | TFLOPs: 62.43 | +[default7]: iteration 2186/ 3814 | consumed samples: 1119232 | consumed tokens: 2292187136 | elapsed time per iteration (s): 6.02 | learning rate: 2.364E-04 | global batch size: 512 | lm loss: 3.455777E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.076 | TFLOPs: 64.26 | +[default7]: iteration 2187/ 3814 | consumed samples: 1119744 | consumed tokens: 2293235712 | elapsed time per iteration (s): 5.95 | learning rate: 2.362E-04 | global batch size: 512 | lm loss: 3.461728E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.979 | TFLOPs: 64.94 | +[default7]: iteration 2188/ 3814 | consumed samples: 1120256 | consumed tokens: 2294284288 | elapsed time per iteration (s): 5.98 | learning rate: 2.360E-04 | global batch size: 512 | lm loss: 3.434661E+00 | loss scale: 65536.0 | grad norm: 0.154 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.628 | TFLOPs: 64.68 | +[default7]: iteration 2189/ 3814 | consumed samples: 1120768 | consumed tokens: 2295332864 | elapsed time per iteration (s): 6.01 | learning rate: 2.357E-04 | global batch size: 512 | lm loss: 3.454270E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.159 | TFLOPs: 64.32 | +[default7]: iteration 2190/ 3814 | consumed samples: 1121280 | consumed tokens: 2296381440 | elapsed time per iteration (s): 6.16 | learning rate: 2.355E-04 | global batch size: 512 | lm loss: 3.437217E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.092 | TFLOPs: 62.76 | +[default7]: iteration 2191/ 3814 | consumed samples: 1121792 | consumed tokens: 2297430016 | elapsed time per iteration (s): 5.97 | learning rate: 2.353E-04 | global batch size: 512 | lm loss: 3.437478E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.726 | TFLOPs: 64.75 | +[default7]: iteration 2192/ 3814 | consumed samples: 1122304 | consumed tokens: 2298478592 | elapsed time per iteration (s): 6.03 | learning rate: 2.350E-04 | global batch size: 512 | lm loss: 3.437554E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.976 | TFLOPs: 64.18 | +[default7]: iteration 2193/ 3814 | consumed samples: 1122816 | consumed tokens: 2299527168 | elapsed time per iteration (s): 6.01 | learning rate: 2.348E-04 | global batch size: 512 | lm loss: 3.466135E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.243 | TFLOPs: 64.39 | +[default7]: iteration 2194/ 3814 | consumed samples: 1123328 | consumed tokens: 2300575744 | elapsed time per iteration (s): 6.11 | learning rate: 2.346E-04 | global batch size: 512 | lm loss: 3.451521E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.775 | TFLOPs: 63.28 | +[default7]: iteration 2195/ 3814 | consumed samples: 1123840 | consumed tokens: 2301624320 | elapsed time per iteration (s): 6.16 | learning rate: 2.343E-04 | global batch size: 512 | lm loss: 3.458169E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.094 | TFLOPs: 62.76 | +[default7]: iteration 2196/ 3814 | consumed samples: 1124352 | consumed tokens: 2302672896 | elapsed time per iteration (s): 6.16 | learning rate: 2.341E-04 | global batch size: 512 | lm loss: 3.416808E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.134 | TFLOPs: 62.79 | +[default7]: iteration 2197/ 3814 | consumed samples: 1124864 | consumed tokens: 2303721472 | elapsed time per iteration (s): 6.15 | learning rate: 2.339E-04 | global batch size: 512 | lm loss: 3.444315E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.255 | TFLOPs: 62.88 | +[default7]: iteration 2198/ 3814 | consumed samples: 1125376 | consumed tokens: 2304770048 | elapsed time per iteration (s): 6.17 | learning rate: 2.336E-04 | global batch size: 512 | lm loss: 3.422992E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.008 | TFLOPs: 62.70 | +[default7]: iteration 2199/ 3814 | consumed samples: 1125888 | consumed tokens: 2305818624 | elapsed time per iteration (s): 5.99 | learning rate: 2.334E-04 | global batch size: 512 | lm loss: 3.394792E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.523 | TFLOPs: 64.60 | +[default7]: iteration 2200/ 3814 | consumed samples: 1126400 | consumed tokens: 2306867200 | elapsed time per iteration (s): 6.16 | learning rate: 2.332E-04 | global batch size: 512 | lm loss: 3.442307E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.180 | TFLOPs: 62.83 | +[default7]: iteration 2201/ 3814 | consumed samples: 1126912 | consumed tokens: 2307915776 | elapsed time per iteration (s): 6.12 | learning rate: 2.329E-04 | global batch size: 512 | lm loss: 3.429051E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.665 | TFLOPs: 63.19 | +[default7]: iteration 2202/ 3814 | consumed samples: 1127424 | consumed tokens: 2308964352 | elapsed time per iteration (s): 6.03 | learning rate: 2.327E-04 | global batch size: 512 | lm loss: 3.443654E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.963 | TFLOPs: 64.17 | +[default7]: iteration 2203/ 3814 | consumed samples: 1127936 | consumed tokens: 2310012928 | elapsed time per iteration (s): 6.02 | learning rate: 2.324E-04 | global batch size: 512 | lm loss: 3.422405E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.040 | TFLOPs: 64.23 | +[default7]: iteration 2204/ 3814 | consumed samples: 1128448 | consumed tokens: 2311061504 | elapsed time per iteration (s): 6.04 | learning rate: 2.322E-04 | global batch size: 512 | lm loss: 3.409924E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.819 | TFLOPs: 64.06 | +[default7]: iteration 2205/ 3814 | consumed samples: 1128960 | consumed tokens: 2312110080 | elapsed time per iteration (s): 6.03 | learning rate: 2.320E-04 | global batch size: 512 | lm loss: 3.449562E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.975 | TFLOPs: 64.18 | +[default7]: iteration 2206/ 3814 | consumed samples: 1129472 | consumed tokens: 2313158656 | elapsed time per iteration (s): 5.85 | learning rate: 2.317E-04 | global batch size: 512 | lm loss: 3.455798E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.596 | TFLOPs: 66.16 | +[default7]: iteration 2207/ 3814 | consumed samples: 1129984 | consumed tokens: 2314207232 | elapsed time per iteration (s): 6.10 | learning rate: 2.315E-04 | global batch size: 512 | lm loss: 3.423799E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.890 | TFLOPs: 63.36 | +[default7]: iteration 2208/ 3814 | consumed samples: 1130496 | consumed tokens: 2315255808 | elapsed time per iteration (s): 6.09 | learning rate: 2.313E-04 | global batch size: 512 | lm loss: 3.432436E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.136 | TFLOPs: 63.55 | +[default7]: iteration 2209/ 3814 | consumed samples: 1131008 | consumed tokens: 2316304384 | elapsed time per iteration (s): 6.01 | learning rate: 2.310E-04 | global batch size: 512 | lm loss: 3.432584E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.206 | TFLOPs: 64.36 | +[default7]: iteration 2210/ 3814 | consumed samples: 1131520 | consumed tokens: 2317352960 | elapsed time per iteration (s): 6.12 | learning rate: 2.308E-04 | global batch size: 512 | lm loss: 3.434756E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.603 | TFLOPs: 63.15 | +[default7]: iteration 2211/ 3814 | consumed samples: 1132032 | consumed tokens: 2318401536 | elapsed time per iteration (s): 6.05 | learning rate: 2.306E-04 | global batch size: 512 | lm loss: 3.410082E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.611 | TFLOPs: 63.91 | +[default7]: iteration 2212/ 3814 | consumed samples: 1132544 | consumed tokens: 2319450112 | elapsed time per iteration (s): 6.12 | learning rate: 2.303E-04 | global batch size: 512 | lm loss: 3.438240E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.689 | TFLOPs: 63.21 | +[default7]: iteration 2213/ 3814 | consumed samples: 1133056 | consumed tokens: 2320498688 | elapsed time per iteration (s): 6.10 | learning rate: 2.301E-04 | global batch size: 512 | lm loss: 3.446395E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.927 | TFLOPs: 63.39 | +[default7]: iteration 2214/ 3814 | consumed samples: 1133568 | consumed tokens: 2321547264 | elapsed time per iteration (s): 6.07 | learning rate: 2.299E-04 | global batch size: 512 | lm loss: 3.426648E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.350 | TFLOPs: 63.71 | +[default7]: iteration 2215/ 3814 | consumed samples: 1134080 | consumed tokens: 2322595840 | elapsed time per iteration (s): 6.08 | learning rate: 2.296E-04 | global batch size: 512 | lm loss: 3.432392E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.236 | TFLOPs: 63.62 | +[default7]: iteration 2216/ 3814 | consumed samples: 1134592 | consumed tokens: 2323644416 | elapsed time per iteration (s): 6.07 | learning rate: 2.294E-04 | global batch size: 512 | lm loss: 3.413079E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.397 | TFLOPs: 63.75 | +[default7]: iteration 2217/ 3814 | consumed samples: 1135104 | consumed tokens: 2324692992 | elapsed time per iteration (s): 6.12 | learning rate: 2.292E-04 | global batch size: 512 | lm loss: 3.415552E+00 | loss scale: 65536.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.631 | TFLOPs: 63.17 | +[default7]: iteration 2218/ 3814 | consumed samples: 1135616 | consumed tokens: 2325741568 | elapsed time per iteration (s): 6.01 | learning rate: 2.289E-04 | global batch size: 512 | lm loss: 3.444117E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.205 | TFLOPs: 64.36 | +[default7]: iteration 2219/ 3814 | consumed samples: 1136128 | consumed tokens: 2326790144 | elapsed time per iteration (s): 6.12 | learning rate: 2.287E-04 | global batch size: 512 | lm loss: 3.411071E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.645 | TFLOPs: 63.18 | +[default7]: iteration 2220/ 3814 | consumed samples: 1136640 | consumed tokens: 2327838720 | elapsed time per iteration (s): 6.11 | learning rate: 2.285E-04 | global batch size: 512 | lm loss: 3.414207E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.798 | TFLOPs: 63.29 | +[default7]: iteration 2221/ 3814 | consumed samples: 1137152 | consumed tokens: 2328887296 | elapsed time per iteration (s): 6.16 | learning rate: 2.282E-04 | global batch size: 512 | lm loss: 3.465378E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.106 | TFLOPs: 62.77 | +[default7]: iteration 2222/ 3814 | consumed samples: 1137664 | consumed tokens: 2329935872 | elapsed time per iteration (s): 5.98 | learning rate: 2.280E-04 | global batch size: 512 | lm loss: 3.413537E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.605 | TFLOPs: 64.66 | +[default7]: iteration 2223/ 3814 | consumed samples: 1138176 | consumed tokens: 2330984448 | elapsed time per iteration (s): 6.14 | learning rate: 2.278E-04 | global batch size: 512 | lm loss: 3.415322E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.436 | TFLOPs: 63.02 | +[default7]: iteration 2224/ 3814 | consumed samples: 1138688 | consumed tokens: 2332033024 | elapsed time per iteration (s): 5.96 | learning rate: 2.275E-04 | global batch size: 512 | lm loss: 3.450394E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.931 | TFLOPs: 64.90 | +[default7]: iteration 2225/ 3814 | consumed samples: 1139200 | consumed tokens: 2333081600 | elapsed time per iteration (s): 6.00 | learning rate: 2.273E-04 | global batch size: 512 | lm loss: 3.459348E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.263 | TFLOPs: 64.40 | +[default7]: iteration 2226/ 3814 | consumed samples: 1139712 | consumed tokens: 2334130176 | elapsed time per iteration (s): 5.95 | learning rate: 2.270E-04 | global batch size: 512 | lm loss: 3.409430E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.030 | TFLOPs: 64.98 | +[default7]: iteration 2227/ 3814 | consumed samples: 1140224 | consumed tokens: 2335178752 | elapsed time per iteration (s): 6.14 | learning rate: 2.268E-04 | global batch size: 512 | lm loss: 3.417027E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.381 | TFLOPs: 62.98 | +[default7]: iteration 2228/ 3814 | consumed samples: 1140736 | consumed tokens: 2336227328 | elapsed time per iteration (s): 6.03 | learning rate: 2.266E-04 | global batch size: 512 | lm loss: 3.441051E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.869 | TFLOPs: 64.10 | +[default7]: iteration 2229/ 3814 | consumed samples: 1141248 | consumed tokens: 2337275904 | elapsed time per iteration (s): 6.01 | learning rate: 2.263E-04 | global batch size: 512 | lm loss: 3.416702E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.257 | TFLOPs: 64.40 | +[default7]: iteration 2230/ 3814 | consumed samples: 1141760 | consumed tokens: 2338324480 | elapsed time per iteration (s): 5.92 | learning rate: 2.261E-04 | global batch size: 512 | lm loss: 3.423057E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.467 | TFLOPs: 65.31 | +[default7]: iteration 2231/ 3814 | consumed samples: 1142272 | consumed tokens: 2339373056 | elapsed time per iteration (s): 6.02 | learning rate: 2.259E-04 | global batch size: 512 | lm loss: 3.382737E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.086 | TFLOPs: 64.27 | +[default7]: iteration 2232/ 3814 | consumed samples: 1142784 | consumed tokens: 2340421632 | elapsed time per iteration (s): 5.93 | learning rate: 2.256E-04 | global batch size: 512 | lm loss: 3.416848E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.357 | TFLOPs: 65.23 | +[default7]: iteration 2233/ 3814 | consumed samples: 1143296 | consumed tokens: 2341470208 | elapsed time per iteration (s): 6.04 | learning rate: 2.254E-04 | global batch size: 512 | lm loss: 3.426229E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.823 | TFLOPs: 64.07 | +[default7]: iteration 2234/ 3814 | consumed samples: 1143808 | consumed tokens: 2342518784 | elapsed time per iteration (s): 6.05 | learning rate: 2.252E-04 | global batch size: 512 | lm loss: 3.434810E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.683 | TFLOPs: 63.96 | +[default7]: iteration 2235/ 3814 | consumed samples: 1144320 | consumed tokens: 2343567360 | elapsed time per iteration (s): 6.01 | learning rate: 2.249E-04 | global batch size: 512 | lm loss: 3.421293E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.156 | TFLOPs: 64.32 | +[default7]: iteration 2236/ 3814 | consumed samples: 1144832 | consumed tokens: 2344615936 | elapsed time per iteration (s): 6.03 | learning rate: 2.247E-04 | global batch size: 512 | lm loss: 3.453338E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.929 | TFLOPs: 64.15 | +[default7]: iteration 2237/ 3814 | consumed samples: 1145344 | consumed tokens: 2345664512 | elapsed time per iteration (s): 6.04 | learning rate: 2.245E-04 | global batch size: 512 | lm loss: 3.404497E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.751 | TFLOPs: 64.01 | +[default7]: iteration 2238/ 3814 | consumed samples: 1145856 | consumed tokens: 2346713088 | elapsed time per iteration (s): 6.09 | learning rate: 2.242E-04 | global batch size: 512 | lm loss: 3.432288E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.128 | TFLOPs: 63.54 | +[default7]: iteration 2239/ 3814 | consumed samples: 1146368 | consumed tokens: 2347761664 | elapsed time per iteration (s): 6.12 | learning rate: 2.240E-04 | global batch size: 512 | lm loss: 3.431326E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.652 | TFLOPs: 63.18 | +[default7]: iteration 2240/ 3814 | consumed samples: 1146880 | consumed tokens: 2348810240 | elapsed time per iteration (s): 6.09 | learning rate: 2.238E-04 | global batch size: 512 | lm loss: 3.406506E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.129 | TFLOPs: 63.54 | +[default7]: iteration 2241/ 3814 | consumed samples: 1147392 | consumed tokens: 2349858816 | elapsed time per iteration (s): 6.02 | learning rate: 2.235E-04 | global batch size: 512 | lm loss: 3.419118E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.099 | TFLOPs: 64.28 | +[default7]: iteration 2242/ 3814 | consumed samples: 1147904 | consumed tokens: 2350907392 | elapsed time per iteration (s): 6.02 | learning rate: 2.233E-04 | global batch size: 512 | lm loss: 3.411104E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.039 | TFLOPs: 64.23 | +[default7]: iteration 2243/ 3814 | consumed samples: 1148416 | consumed tokens: 2351955968 | elapsed time per iteration (s): 5.98 | learning rate: 2.231E-04 | global batch size: 512 | lm loss: 3.404529E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.637 | TFLOPs: 64.68 | +[default7]: iteration 2244/ 3814 | consumed samples: 1148928 | consumed tokens: 2353004544 | elapsed time per iteration (s): 6.01 | learning rate: 2.228E-04 | global batch size: 512 | lm loss: 3.438872E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.159 | TFLOPs: 64.32 | +[default7]: iteration 2245/ 3814 | consumed samples: 1149440 | consumed tokens: 2354053120 | elapsed time per iteration (s): 6.00 | learning rate: 2.226E-04 | global batch size: 512 | lm loss: 3.420522E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.275 | TFLOPs: 64.41 | +[default7]: iteration 2246/ 3814 | consumed samples: 1149952 | consumed tokens: 2355101696 | elapsed time per iteration (s): 5.97 | learning rate: 2.224E-04 | global batch size: 512 | lm loss: 3.422722E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.751 | TFLOPs: 64.77 | +[default7]: iteration 2247/ 3814 | consumed samples: 1150464 | consumed tokens: 2356150272 | elapsed time per iteration (s): 6.00 | learning rate: 2.221E-04 | global batch size: 512 | lm loss: 3.428001E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 2248/ 3814 | consumed samples: 1150976 | consumed tokens: 2357198848 | elapsed time per iteration (s): 6.02 | learning rate: 2.219E-04 | global batch size: 512 | lm loss: 3.419310E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.033 | TFLOPs: 64.23 | +[default7]: iteration 2249/ 3814 | consumed samples: 1151488 | consumed tokens: 2358247424 | elapsed time per iteration (s): 6.03 | learning rate: 2.217E-04 | global batch size: 512 | lm loss: 3.369959E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.932 | TFLOPs: 64.15 | +[default7]: iteration 2250/ 3814 | consumed samples: 1152000 | consumed tokens: 2359296000 | elapsed time per iteration (s): 5.87 | learning rate: 2.214E-04 | global batch size: 512 | lm loss: 3.400410E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.252 | TFLOPs: 65.90 | +[default1]:[2023-02-16 11:18:11,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 2250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 11:18:11,925] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2250 is begin to save! +[default0]:[2023-02-16 11:18:11,929] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,093] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,094] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,087] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,088] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,142] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,142] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,150] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,150] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,205] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,206] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,198] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,199] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,254] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,262] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,263] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,319] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,310] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,366] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,374] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,375] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,421] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,421] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,484] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,484] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,494] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,537] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,537] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,548] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,549] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,607] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,593] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,594] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,653] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,653] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,666] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,717] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,717] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,774] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,775] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,790] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,832] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,833] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,845] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,846] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:12,901] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,901] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:12,888] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,889] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:12,950] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:12,950] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:12,958] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:12,959] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,015] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,016] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,004] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,004] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,061] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,062] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,073] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,118] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,118] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,178] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,129] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,130] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,186] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,236] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,237] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,242] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,243] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,312] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,310] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,311] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,375] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,376] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,380] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,432] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,433] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,438] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,438] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,494] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,543] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,550] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,607] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,608] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,598] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,599] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,657] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,668] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,714] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,715] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,774] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,728] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,786] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,786] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,843] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,844] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 11:18:13,852] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,852] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,909] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 11:18:13,900] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,900] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,962] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,962] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 11:18:13,963] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 11:18:13,964] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_01_model_states.pt +[default1]:[2023-02-16 11:18:13,965] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 11:18:13,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_01_model_states.pt. +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:18:13,964] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,964] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 11:18:13,965] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 11:18:13,966] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_00_model_states.pt +[default0]:[2023-02-16 11:18:13,966] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 11:18:13,969] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:18:13,992] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:18:14,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,490] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,490] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,516] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,516] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,516] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,562] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,562] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,562] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,585] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,586] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,586] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,544] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,568] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,568] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,568] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,513] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,513] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,513] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,543] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,544] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,544] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,584] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,584] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,584] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,606] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,606] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,606] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,599] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,599] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,529] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,529] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,533] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,533] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,533] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,552] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,552] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,552] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,542] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,542] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,550] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,551] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,551] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,641] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,641] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,641] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,579] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,579] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,579] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,565] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,565] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,566] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,603] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,603] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,591] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,591] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,612] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,612] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,625] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,625] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,625] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,673] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,673] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,673] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,693] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,694] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,694] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,638] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,638] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,638] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,658] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,658] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,658] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,599] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,599] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,600] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,630] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,630] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,630] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,675] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,675] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,675] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,700] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,700] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,645] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,645] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,645] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,665] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,665] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,643] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,643] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,643] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,667] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,667] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,667] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,695] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,695] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,652] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,652] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,652] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,727] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,718] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,718] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,718] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,664] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,664] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,737] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,737] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,737] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,692] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,693] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,693] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,700] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,701] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,701] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default1]:[2023-02-16 11:18:14,683] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:18:14,683] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:18:14,683] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default3]:[2023-02-16 11:18:14,730] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:18:14,730] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:18:14,730] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,763] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,763] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,763] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,720] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,720] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,743] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,743] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,743] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,724] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,724] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,727] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,727] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,727] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,793] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,773] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,773] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,773] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default2]:[2023-02-16 11:18:14,770] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:18:14,770] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:18:14,770] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,761] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,761] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,761] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]:[2023-02-16 11:18:14,793] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:18:14,793] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:18:14,793] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,781] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,781] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,781] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,799] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,799] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,799] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,820] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,820] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,820] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,815] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,815] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,815] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default6]:[2023-02-16 11:18:14,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:18:14,961] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:18:14,962] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,895] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,896] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,896] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default5]:[2023-02-16 11:18:14,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:18:14,986] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:18:14,986] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default4]:[2023-02-16 11:18:14,994] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:18:14,994] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:18:14,994] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default7]:[2023-02-16 11:18:14,956] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:18:14,956] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2250/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:18:14,956] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2250 is ready now! +[default0]: successfully saved checkpoint at iteration 2250 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:time (ms) | save-checkpoint: 3079.28 +[default7]: iteration 2251/ 3814 | consumed samples: 1152512 | consumed tokens: 2360344576 | elapsed time per iteration (s): 9.10 | learning rate: 2.212E-04 | global batch size: 512 | lm loss: 3.419653E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 56.267 | TFLOPs: 42.50 | +[default7]: iteration 2252/ 3814 | consumed samples: 1153024 | consumed tokens: 2361393152 | elapsed time per iteration (s): 5.93 | learning rate: 2.210E-04 | global batch size: 512 | lm loss: 3.401738E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.304 | TFLOPs: 65.19 | +[default7]: iteration 2253/ 3814 | consumed samples: 1153536 | consumed tokens: 2362441728 | elapsed time per iteration (s): 6.13 | learning rate: 2.207E-04 | global batch size: 512 | lm loss: 3.408611E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.557 | TFLOPs: 63.11 | +[default7]: iteration 2254/ 3814 | consumed samples: 1154048 | consumed tokens: 2363490304 | elapsed time per iteration (s): 6.16 | learning rate: 2.205E-04 | global batch size: 512 | lm loss: 3.421926E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.174 | TFLOPs: 62.82 | +[default7]: iteration 2255/ 3814 | consumed samples: 1154560 | consumed tokens: 2364538880 | elapsed time per iteration (s): 6.12 | learning rate: 2.203E-04 | global batch size: 512 | lm loss: 3.417478E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.704 | TFLOPs: 63.22 | +[default7]: iteration 2256/ 3814 | consumed samples: 1155072 | consumed tokens: 2365587456 | elapsed time per iteration (s): 6.11 | learning rate: 2.200E-04 | global batch size: 512 | lm loss: 3.407668E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.793 | TFLOPs: 63.29 | +[default7]: iteration 2257/ 3814 | consumed samples: 1155584 | consumed tokens: 2366636032 | elapsed time per iteration (s): 6.04 | learning rate: 2.198E-04 | global batch size: 512 | lm loss: 3.412046E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.834 | TFLOPs: 64.08 | +[default7]: iteration 2258/ 3814 | consumed samples: 1156096 | consumed tokens: 2367684608 | elapsed time per iteration (s): 6.14 | learning rate: 2.196E-04 | global batch size: 512 | lm loss: 3.409071E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.387 | TFLOPs: 62.98 | +[default7]: iteration 2259/ 3814 | consumed samples: 1156608 | consumed tokens: 2368733184 | elapsed time per iteration (s): 6.14 | learning rate: 2.193E-04 | global batch size: 512 | lm loss: 3.423677E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.385 | TFLOPs: 62.98 | +[default7]: iteration 2260/ 3814 | consumed samples: 1157120 | consumed tokens: 2369781760 | elapsed time per iteration (s): 5.96 | learning rate: 2.191E-04 | global batch size: 512 | lm loss: 3.434643E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.934 | TFLOPs: 64.91 | +[default7]: iteration 2261/ 3814 | consumed samples: 1157632 | consumed tokens: 2370830336 | elapsed time per iteration (s): 6.01 | learning rate: 2.189E-04 | global batch size: 512 | lm loss: 3.394883E+00 | loss scale: 65536.0 | grad norm: 0.152 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.141 | TFLOPs: 64.31 | +[default7]: iteration 2262/ 3814 | consumed samples: 1158144 | consumed tokens: 2371878912 | elapsed time per iteration (s): 5.92 | learning rate: 2.186E-04 | global batch size: 512 | lm loss: 3.403409E+00 | loss scale: 65536.0 | grad norm: 0.165 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.514 | TFLOPs: 65.34 | +[default7]: iteration 2263/ 3814 | consumed samples: 1158656 | consumed tokens: 2372927488 | elapsed time per iteration (s): 6.03 | learning rate: 2.184E-04 | global batch size: 512 | lm loss: 3.409770E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.881 | TFLOPs: 64.11 | +[default7]: iteration 2264/ 3814 | consumed samples: 1159168 | consumed tokens: 2373976064 | elapsed time per iteration (s): 5.99 | learning rate: 2.182E-04 | global batch size: 512 | lm loss: 3.393392E+00 | loss scale: 65536.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.479 | TFLOPs: 64.56 | +[default7]: iteration 2265/ 3814 | consumed samples: 1159680 | consumed tokens: 2375024640 | elapsed time per iteration (s): 6.00 | learning rate: 2.179E-04 | global batch size: 512 | lm loss: 3.391360E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.276 | TFLOPs: 64.41 | +[default7]: iteration 2266/ 3814 | consumed samples: 1160192 | consumed tokens: 2376073216 | elapsed time per iteration (s): 6.05 | learning rate: 2.177E-04 | global batch size: 512 | lm loss: 3.407573E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.690 | TFLOPs: 63.97 | +[default7]: iteration 2267/ 3814 | consumed samples: 1160704 | consumed tokens: 2377121792 | elapsed time per iteration (s): 6.02 | learning rate: 2.175E-04 | global batch size: 512 | lm loss: 3.459448E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.097 | TFLOPs: 64.27 | +[default7]: iteration 2268/ 3814 | consumed samples: 1161216 | consumed tokens: 2378170368 | elapsed time per iteration (s): 5.92 | learning rate: 2.172E-04 | global batch size: 512 | lm loss: 3.400061E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.524 | TFLOPs: 65.35 | +[default7]: iteration 2269/ 3814 | consumed samples: 1161728 | consumed tokens: 2379218944 | elapsed time per iteration (s): 6.00 | learning rate: 2.170E-04 | global batch size: 512 | lm loss: 3.431089E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.280 | TFLOPs: 64.41 | +[default7]: iteration 2270/ 3814 | consumed samples: 1162240 | consumed tokens: 2380267520 | elapsed time per iteration (s): 5.95 | learning rate: 2.168E-04 | global batch size: 512 | lm loss: 3.406248E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.086 | TFLOPs: 65.02 | +[default7]: iteration 2271/ 3814 | consumed samples: 1162752 | consumed tokens: 2381316096 | elapsed time per iteration (s): 5.98 | learning rate: 2.165E-04 | global batch size: 512 | lm loss: 3.410332E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.575 | TFLOPs: 64.64 | +[default7]: iteration 2272/ 3814 | consumed samples: 1163264 | consumed tokens: 2382364672 | elapsed time per iteration (s): 6.05 | learning rate: 2.163E-04 | global batch size: 512 | lm loss: 3.439456E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.566 | TFLOPs: 63.87 | +[default7]: iteration 2273/ 3814 | consumed samples: 1163776 | consumed tokens: 2383413248 | elapsed time per iteration (s): 6.14 | learning rate: 2.161E-04 | global batch size: 512 | lm loss: 3.408880E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.336 | TFLOPs: 62.94 | +[default7]: iteration 2274/ 3814 | consumed samples: 1164288 | consumed tokens: 2384461824 | elapsed time per iteration (s): 6.01 | learning rate: 2.158E-04 | global batch size: 512 | lm loss: 3.426542E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.146 | TFLOPs: 64.31 | +[default7]: iteration 2275/ 3814 | consumed samples: 1164800 | consumed tokens: 2385510400 | elapsed time per iteration (s): 5.98 | learning rate: 2.156E-04 | global batch size: 512 | lm loss: 3.459356E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.594 | TFLOPs: 64.65 | +[default7]: iteration 2276/ 3814 | consumed samples: 1165312 | consumed tokens: 2386558976 | elapsed time per iteration (s): 5.99 | learning rate: 2.154E-04 | global batch size: 512 | lm loss: 3.419228E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.441 | TFLOPs: 64.53 | +[default7]: iteration 2277/ 3814 | consumed samples: 1165824 | consumed tokens: 2387607552 | elapsed time per iteration (s): 5.97 | learning rate: 2.151E-04 | global batch size: 512 | lm loss: 3.425301E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.765 | TFLOPs: 64.78 | +[default7]: iteration 2278/ 3814 | consumed samples: 1166336 | consumed tokens: 2388656128 | elapsed time per iteration (s): 5.97 | learning rate: 2.149E-04 | global batch size: 512 | lm loss: 3.414628E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.736 | TFLOPs: 64.76 | +[default7]: iteration 2279/ 3814 | consumed samples: 1166848 | consumed tokens: 2389704704 | elapsed time per iteration (s): 5.98 | learning rate: 2.147E-04 | global batch size: 512 | lm loss: 3.415941E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.654 | TFLOPs: 64.70 | +[default7]: iteration 2280/ 3814 | consumed samples: 1167360 | consumed tokens: 2390753280 | elapsed time per iteration (s): 5.99 | learning rate: 2.144E-04 | global batch size: 512 | lm loss: 3.420957E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.538 | TFLOPs: 64.61 | +[default7]: iteration 2281/ 3814 | consumed samples: 1167872 | consumed tokens: 2391801856 | elapsed time per iteration (s): 6.00 | learning rate: 2.142E-04 | global batch size: 512 | lm loss: 3.426327E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.337 | TFLOPs: 64.46 | +[default7]: iteration 2282/ 3814 | consumed samples: 1168384 | consumed tokens: 2392850432 | elapsed time per iteration (s): 6.10 | learning rate: 2.140E-04 | global batch size: 512 | lm loss: 3.395088E+00 | loss scale: 65536.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.905 | TFLOPs: 63.37 | +[default7]: iteration 2283/ 3814 | consumed samples: 1168896 | consumed tokens: 2393899008 | elapsed time per iteration (s): 6.03 | learning rate: 2.137E-04 | global batch size: 512 | lm loss: 3.391134E+00 | loss scale: 65536.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.970 | TFLOPs: 64.18 | +[default7]: iteration 2284/ 3814 | consumed samples: 1169408 | consumed tokens: 2394947584 | elapsed time per iteration (s): 6.14 | learning rate: 2.135E-04 | global batch size: 512 | lm loss: 3.430803E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.384 | TFLOPs: 62.98 | +[default7]: iteration 2285/ 3814 | consumed samples: 1169920 | consumed tokens: 2395996160 | elapsed time per iteration (s): 6.07 | learning rate: 2.133E-04 | global batch size: 512 | lm loss: 3.398805E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.298 | TFLOPs: 63.67 | +[default7]: iteration 2286/ 3814 | consumed samples: 1170432 | consumed tokens: 2397044736 | elapsed time per iteration (s): 6.03 | learning rate: 2.130E-04 | global batch size: 512 | lm loss: 3.400982E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.958 | TFLOPs: 64.17 | +[default7]: iteration 2287/ 3814 | consumed samples: 1170944 | consumed tokens: 2398093312 | elapsed time per iteration (s): 6.14 | learning rate: 2.128E-04 | global batch size: 512 | lm loss: 3.397881E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.445 | TFLOPs: 63.03 | +[default7]: iteration 2288/ 3814 | consumed samples: 1171456 | consumed tokens: 2399141888 | elapsed time per iteration (s): 6.06 | learning rate: 2.126E-04 | global batch size: 512 | lm loss: 3.405508E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.553 | TFLOPs: 63.86 | +[default7]: iteration 2289/ 3814 | consumed samples: 1171968 | consumed tokens: 2400190464 | elapsed time per iteration (s): 6.12 | learning rate: 2.123E-04 | global batch size: 512 | lm loss: 3.416485E+00 | loss scale: 65536.0 | grad norm: 0.149 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.624 | TFLOPs: 63.16 | +[default7]: iteration 2290/ 3814 | consumed samples: 1172480 | consumed tokens: 2401239040 | elapsed time per iteration (s): 6.00 | learning rate: 2.121E-04 | global batch size: 512 | lm loss: 3.444366E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.320 | TFLOPs: 64.44 | +[default7]: iteration 2291/ 3814 | consumed samples: 1172992 | consumed tokens: 2402287616 | elapsed time per iteration (s): 6.11 | learning rate: 2.119E-04 | global batch size: 512 | lm loss: 3.417645E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.830 | TFLOPs: 63.32 | +[default7]: iteration 2292/ 3814 | consumed samples: 1173504 | consumed tokens: 2403336192 | elapsed time per iteration (s): 6.12 | learning rate: 2.116E-04 | global batch size: 512 | lm loss: 3.419889E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.704 | TFLOPs: 63.22 | +[default7]: iteration 2293/ 3814 | consumed samples: 1174016 | consumed tokens: 2404384768 | elapsed time per iteration (s): 6.11 | learning rate: 2.114E-04 | global batch size: 512 | lm loss: 3.435353E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.812 | TFLOPs: 63.30 | +[default7]: iteration 2294/ 3814 | consumed samples: 1174528 | consumed tokens: 2405433344 | elapsed time per iteration (s): 6.14 | learning rate: 2.112E-04 | global batch size: 512 | lm loss: 3.434777E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.410 | TFLOPs: 63.00 | +[default7]: iteration 2295/ 3814 | consumed samples: 1175040 | consumed tokens: 2406481920 | elapsed time per iteration (s): 6.20 | learning rate: 2.110E-04 | global batch size: 512 | lm loss: 3.440277E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.615 | TFLOPs: 62.40 | +[default7]: iteration 2296/ 3814 | consumed samples: 1175552 | consumed tokens: 2407530496 | elapsed time per iteration (s): 6.15 | learning rate: 2.107E-04 | global batch size: 512 | lm loss: 3.412720E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.312 | TFLOPs: 62.93 | +[default7]: iteration 2297/ 3814 | consumed samples: 1176064 | consumed tokens: 2408579072 | elapsed time per iteration (s): 6.13 | learning rate: 2.105E-04 | global batch size: 512 | lm loss: 3.366879E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.559 | TFLOPs: 63.11 | +[default7]: iteration 2298/ 3814 | consumed samples: 1176576 | consumed tokens: 2409627648 | elapsed time per iteration (s): 6.17 | learning rate: 2.103E-04 | global batch size: 512 | lm loss: 3.423760E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.963 | TFLOPs: 62.66 | +[default7]: iteration 2299/ 3814 | consumed samples: 1177088 | consumed tokens: 2410676224 | elapsed time per iteration (s): 6.09 | learning rate: 2.100E-04 | global batch size: 512 | lm loss: 3.417686E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.084 | TFLOPs: 63.51 | +[default7]: iteration 2300/ 3814 | consumed samples: 1177600 | consumed tokens: 2411724800 | elapsed time per iteration (s): 6.14 | learning rate: 2.098E-04 | global batch size: 512 | lm loss: 3.429454E+00 | loss scale: 65536.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.417 | TFLOPs: 63.01 | +[default7]: iteration 2301/ 3814 | consumed samples: 1178112 | consumed tokens: 2412773376 | elapsed time per iteration (s): 6.11 | learning rate: 2.096E-04 | global batch size: 512 | lm loss: 3.431017E+00 | loss scale: 65536.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.818 | TFLOPs: 63.31 | +[default7]: iteration 2302/ 3814 | consumed samples: 1178624 | consumed tokens: 2413821952 | elapsed time per iteration (s): 6.15 | learning rate: 2.093E-04 | global batch size: 512 | lm loss: 3.394275E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.212 | TFLOPs: 62.85 | +[default7]: iteration 2303/ 3814 | consumed samples: 1179136 | consumed tokens: 2414870528 | elapsed time per iteration (s): 6.08 | learning rate: 2.091E-04 | global batch size: 512 | lm loss: 3.410421E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.161 | TFLOPs: 63.57 | +[default7]: iteration 2304/ 3814 | consumed samples: 1179648 | consumed tokens: 2415919104 | elapsed time per iteration (s): 6.11 | learning rate: 2.089E-04 | global batch size: 512 | lm loss: 3.434714E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.811 | TFLOPs: 63.30 | +[default7]: iteration 2305/ 3814 | consumed samples: 1180160 | consumed tokens: 2416967680 | elapsed time per iteration (s): 6.01 | learning rate: 2.086E-04 | global batch size: 512 | lm loss: 3.417446E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.136 | TFLOPs: 64.30 | +[default7]: iteration 2306/ 3814 | consumed samples: 1180672 | consumed tokens: 2418016256 | elapsed time per iteration (s): 6.15 | learning rate: 2.084E-04 | global batch size: 512 | lm loss: 3.400457E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.303 | TFLOPs: 62.92 | +[default7]: iteration 2307/ 3814 | consumed samples: 1181184 | consumed tokens: 2419064832 | elapsed time per iteration (s): 6.14 | learning rate: 2.082E-04 | global batch size: 512 | lm loss: 3.424941E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.411 | TFLOPs: 63.00 | +[default7]: iteration 2308/ 3814 | consumed samples: 1181696 | consumed tokens: 2420113408 | elapsed time per iteration (s): 6.10 | learning rate: 2.079E-04 | global batch size: 512 | lm loss: 3.414397E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.937 | TFLOPs: 63.40 | +[default7]: iteration 2309/ 3814 | consumed samples: 1182208 | consumed tokens: 2421161984 | elapsed time per iteration (s): 6.15 | learning rate: 2.077E-04 | global batch size: 512 | lm loss: 3.390104E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.245 | TFLOPs: 62.88 | +[default7]: iteration 2310/ 3814 | consumed samples: 1182720 | consumed tokens: 2422210560 | elapsed time per iteration (s): 6.17 | learning rate: 2.075E-04 | global batch size: 512 | lm loss: 3.380552E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.045 | TFLOPs: 62.72 | +[default7]: iteration 2311/ 3814 | consumed samples: 1183232 | consumed tokens: 2423259136 | elapsed time per iteration (s): 5.98 | learning rate: 2.072E-04 | global batch size: 512 | lm loss: 3.423463E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.654 | TFLOPs: 64.70 | +[default7]: iteration 2312/ 3814 | consumed samples: 1183744 | consumed tokens: 2424307712 | elapsed time per iteration (s): 5.91 | learning rate: 2.070E-04 | global batch size: 512 | lm loss: 3.403563E+00 | loss scale: 65536.0 | grad norm: 0.161 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.575 | TFLOPs: 65.39 | +[default7]: iteration 2313/ 3814 | consumed samples: 1184256 | consumed tokens: 2425356288 | elapsed time per iteration (s): 5.99 | learning rate: 2.068E-04 | global batch size: 512 | lm loss: 3.404647E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.475 | TFLOPs: 64.56 | +[default7]: iteration 2314/ 3814 | consumed samples: 1184768 | consumed tokens: 2426404864 | elapsed time per iteration (s): 5.86 | learning rate: 2.066E-04 | global batch size: 512 | lm loss: 3.393779E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.351 | TFLOPs: 65.98 | +[default7]: iteration 2315/ 3814 | consumed samples: 1185280 | consumed tokens: 2427453440 | elapsed time per iteration (s): 5.96 | learning rate: 2.063E-04 | global batch size: 512 | lm loss: 3.401482E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.864 | TFLOPs: 64.85 | +[default7]: iteration 2316/ 3814 | consumed samples: 1185792 | consumed tokens: 2428502016 | elapsed time per iteration (s): 5.98 | learning rate: 2.061E-04 | global batch size: 512 | lm loss: 3.370348E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.619 | TFLOPs: 64.67 | +[default7]: iteration 2317/ 3814 | consumed samples: 1186304 | consumed tokens: 2429550592 | elapsed time per iteration (s): 6.04 | learning rate: 2.059E-04 | global batch size: 512 | lm loss: 3.375392E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.829 | TFLOPs: 64.07 | +[default7]: iteration 2318/ 3814 | consumed samples: 1186816 | consumed tokens: 2430599168 | elapsed time per iteration (s): 5.93 | learning rate: 2.056E-04 | global batch size: 512 | lm loss: 3.414223E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.331 | TFLOPs: 65.21 | +[default7]: iteration 2319/ 3814 | consumed samples: 1187328 | consumed tokens: 2431647744 | elapsed time per iteration (s): 6.04 | learning rate: 2.054E-04 | global batch size: 512 | lm loss: 3.423359E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.802 | TFLOPs: 64.05 | +[default7]: iteration 2320/ 3814 | consumed samples: 1187840 | consumed tokens: 2432696320 | elapsed time per iteration (s): 5.91 | learning rate: 2.052E-04 | global batch size: 512 | lm loss: 3.400048E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.560 | TFLOPs: 65.38 | +[default7]: iteration 2321/ 3814 | consumed samples: 1188352 | consumed tokens: 2433744896 | elapsed time per iteration (s): 5.98 | learning rate: 2.049E-04 | global batch size: 512 | lm loss: 3.421834E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.690 | TFLOPs: 64.72 | +[default7]: iteration 2322/ 3814 | consumed samples: 1188864 | consumed tokens: 2434793472 | elapsed time per iteration (s): 5.98 | learning rate: 2.047E-04 | global batch size: 512 | lm loss: 3.394733E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.576 | TFLOPs: 64.64 | +[default7]: iteration 2323/ 3814 | consumed samples: 1189376 | consumed tokens: 2435842048 | elapsed time per iteration (s): 6.07 | learning rate: 2.045E-04 | global batch size: 512 | lm loss: 3.414837E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.321 | TFLOPs: 63.69 | +[default7]: iteration 2324/ 3814 | consumed samples: 1189888 | consumed tokens: 2436890624 | elapsed time per iteration (s): 5.98 | learning rate: 2.042E-04 | global batch size: 512 | lm loss: 3.404362E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.683 | TFLOPs: 64.72 | +[default7]: iteration 2325/ 3814 | consumed samples: 1190400 | consumed tokens: 2437939200 | elapsed time per iteration (s): 6.00 | learning rate: 2.040E-04 | global batch size: 512 | lm loss: 3.412502E+00 | loss scale: 65536.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.387 | TFLOPs: 64.49 | +[default7]: iteration 2326/ 3814 | consumed samples: 1190912 | consumed tokens: 2438987776 | elapsed time per iteration (s): 6.02 | learning rate: 2.038E-04 | global batch size: 512 | lm loss: 3.390123E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.984 | TFLOPs: 64.19 | +[default7]: iteration 2327/ 3814 | consumed samples: 1191424 | consumed tokens: 2440036352 | elapsed time per iteration (s): 6.02 | learning rate: 2.035E-04 | global batch size: 512 | lm loss: 3.365321E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.035 | TFLOPs: 64.23 | +[default7]: iteration 2328/ 3814 | consumed samples: 1191936 | consumed tokens: 2441084928 | elapsed time per iteration (s): 6.02 | learning rate: 2.033E-04 | global batch size: 512 | lm loss: 3.398698E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.076 | TFLOPs: 64.26 | +[default7]: iteration 2329/ 3814 | consumed samples: 1192448 | consumed tokens: 2442133504 | elapsed time per iteration (s): 6.01 | learning rate: 2.031E-04 | global batch size: 512 | lm loss: 3.410271E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.215 | TFLOPs: 64.36 | +[default7]: iteration 2330/ 3814 | consumed samples: 1192960 | consumed tokens: 2443182080 | elapsed time per iteration (s): 5.92 | learning rate: 2.029E-04 | global batch size: 512 | lm loss: 3.402608E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.491 | TFLOPs: 65.33 | +[default7]: iteration 2331/ 3814 | consumed samples: 1193472 | consumed tokens: 2444230656 | elapsed time per iteration (s): 6.03 | learning rate: 2.026E-04 | global batch size: 512 | lm loss: 3.394266E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.858 | TFLOPs: 64.09 | +[default7]: iteration 2332/ 3814 | consumed samples: 1193984 | consumed tokens: 2445279232 | elapsed time per iteration (s): 5.95 | learning rate: 2.024E-04 | global batch size: 512 | lm loss: 3.410010E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.034 | TFLOPs: 64.98 | +[default7]: iteration 2333/ 3814 | consumed samples: 1194496 | consumed tokens: 2446327808 | elapsed time per iteration (s): 6.01 | learning rate: 2.022E-04 | global batch size: 512 | lm loss: 3.407687E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.163 | TFLOPs: 64.32 | +[default7]: iteration 2334/ 3814 | consumed samples: 1195008 | consumed tokens: 2447376384 | elapsed time per iteration (s): 6.00 | learning rate: 2.019E-04 | global batch size: 512 | lm loss: 3.392887E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.266 | TFLOPs: 64.40 | +[default7]: iteration 2335/ 3814 | consumed samples: 1195520 | consumed tokens: 2448424960 | elapsed time per iteration (s): 6.06 | learning rate: 2.017E-04 | global batch size: 512 | lm loss: 3.402208E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.440 | TFLOPs: 63.78 | +[default7]: iteration 2336/ 3814 | consumed samples: 1196032 | consumed tokens: 2449473536 | elapsed time per iteration (s): 5.91 | learning rate: 2.015E-04 | global batch size: 512 | lm loss: 3.415230E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.695 | TFLOPs: 65.48 | +[default7]: iteration 2337/ 3814 | consumed samples: 1196544 | consumed tokens: 2450522112 | elapsed time per iteration (s): 6.02 | learning rate: 2.012E-04 | global batch size: 512 | lm loss: 3.408487E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.005 | TFLOPs: 64.20 | +[default7]: iteration 2338/ 3814 | consumed samples: 1197056 | consumed tokens: 2451570688 | elapsed time per iteration (s): 6.05 | learning rate: 2.010E-04 | global batch size: 512 | lm loss: 3.390751E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.582 | TFLOPs: 63.89 | +[default7]: iteration 2339/ 3814 | consumed samples: 1197568 | consumed tokens: 2452619264 | elapsed time per iteration (s): 6.02 | learning rate: 2.008E-04 | global batch size: 512 | lm loss: 3.391904E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.044 | TFLOPs: 64.23 | +[default7]: iteration 2340/ 3814 | consumed samples: 1198080 | consumed tokens: 2453667840 | elapsed time per iteration (s): 5.86 | learning rate: 2.006E-04 | global batch size: 512 | lm loss: 3.430356E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.361 | TFLOPs: 65.98 | +[default7]: iteration 2341/ 3814 | consumed samples: 1198592 | consumed tokens: 2454716416 | elapsed time per iteration (s): 6.04 | learning rate: 2.003E-04 | global batch size: 512 | lm loss: 3.399496E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.699 | TFLOPs: 63.97 | +[default7]: iteration 2342/ 3814 | consumed samples: 1199104 | consumed tokens: 2455764992 | elapsed time per iteration (s): 5.95 | learning rate: 2.001E-04 | global batch size: 512 | lm loss: 3.366424E+00 | loss scale: 65536.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.066 | TFLOPs: 65.01 | +[default7]: iteration 2343/ 3814 | consumed samples: 1199616 | consumed tokens: 2456813568 | elapsed time per iteration (s): 6.04 | learning rate: 1.999E-04 | global batch size: 512 | lm loss: 3.423424E+00 | loss scale: 65536.0 | grad norm: 0.105 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.751 | TFLOPs: 64.01 | +[default7]: iteration 2344/ 3814 | consumed samples: 1200128 | consumed tokens: 2457862144 | elapsed time per iteration (s): 5.96 | learning rate: 1.996E-04 | global batch size: 512 | lm loss: 3.386295E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.913 | TFLOPs: 64.89 | +[default7]: iteration 2345/ 3814 | consumed samples: 1200640 | consumed tokens: 2458910720 | elapsed time per iteration (s): 6.02 | learning rate: 1.994E-04 | global batch size: 512 | lm loss: 3.386502E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.001 | TFLOPs: 64.20 | +[default7]: iteration 2346/ 3814 | consumed samples: 1201152 | consumed tokens: 2459959296 | elapsed time per iteration (s): 6.07 | learning rate: 1.992E-04 | global batch size: 512 | lm loss: 3.413433E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.364 | TFLOPs: 63.72 | +[default7]: iteration 2347/ 3814 | consumed samples: 1201664 | consumed tokens: 2461007872 | elapsed time per iteration (s): 6.05 | learning rate: 1.989E-04 | global batch size: 512 | lm loss: 3.381172E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.646 | TFLOPs: 63.93 | +[default7]: iteration 2348/ 3814 | consumed samples: 1202176 | consumed tokens: 2462056448 | elapsed time per iteration (s): 6.08 | learning rate: 1.987E-04 | global batch size: 512 | lm loss: 3.408456E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.223 | TFLOPs: 63.61 | +[default7]: iteration 2349/ 3814 | consumed samples: 1202688 | consumed tokens: 2463105024 | elapsed time per iteration (s): 6.08 | learning rate: 1.985E-04 | global batch size: 512 | lm loss: 3.390413E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.255 | TFLOPs: 63.64 | +[default7]: iteration 2350/ 3814 | consumed samples: 1203200 | consumed tokens: 2464153600 | elapsed time per iteration (s): 6.00 | learning rate: 1.983E-04 | global batch size: 512 | lm loss: 3.391568E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.308 | TFLOPs: 64.43 | +[default7]: iteration 2351/ 3814 | consumed samples: 1203712 | consumed tokens: 2465202176 | elapsed time per iteration (s): 6.01 | learning rate: 1.980E-04 | global batch size: 512 | lm loss: 3.378847E+00 | loss scale: 65536.0 | grad norm: 0.153 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.123 | TFLOPs: 64.29 | +[default7]: iteration 2352/ 3814 | consumed samples: 1204224 | consumed tokens: 2466250752 | elapsed time per iteration (s): 6.07 | learning rate: 1.978E-04 | global batch size: 512 | lm loss: 3.405073E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.360 | TFLOPs: 63.72 | +[default7]: iteration 2353/ 3814 | consumed samples: 1204736 | consumed tokens: 2467299328 | elapsed time per iteration (s): 6.02 | learning rate: 1.976E-04 | global batch size: 512 | lm loss: 3.368651E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.014 | TFLOPs: 64.21 | +[default7]: iteration 2354/ 3814 | consumed samples: 1205248 | consumed tokens: 2468347904 | elapsed time per iteration (s): 6.02 | learning rate: 1.973E-04 | global batch size: 512 | lm loss: 3.389539E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.100 | TFLOPs: 64.28 | +[default7]: iteration 2355/ 3814 | consumed samples: 1205760 | consumed tokens: 2469396480 | elapsed time per iteration (s): 6.07 | learning rate: 1.971E-04 | global batch size: 512 | lm loss: 3.401005E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.344 | TFLOPs: 63.71 | +[default7]: iteration 2356/ 3814 | consumed samples: 1206272 | consumed tokens: 2470445056 | elapsed time per iteration (s): 6.09 | learning rate: 1.969E-04 | global batch size: 512 | lm loss: 3.370331E+00 | loss scale: 65536.0 | grad norm: 0.148 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.016 | TFLOPs: 63.46 | +[default7]: iteration 2357/ 3814 | consumed samples: 1206784 | consumed tokens: 2471493632 | elapsed time per iteration (s): 6.05 | learning rate: 1.967E-04 | global batch size: 512 | lm loss: 3.410424E+00 | loss scale: 65536.0 | grad norm: 0.146 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.633 | TFLOPs: 63.92 | +[default7]: iteration 2358/ 3814 | consumed samples: 1207296 | consumed tokens: 2472542208 | elapsed time per iteration (s): 6.02 | learning rate: 1.964E-04 | global batch size: 512 | lm loss: 3.413338E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.053 | TFLOPs: 64.24 | +[default7]: iteration 2359/ 3814 | consumed samples: 1207808 | consumed tokens: 2473590784 | elapsed time per iteration (s): 6.07 | learning rate: 1.962E-04 | global batch size: 512 | lm loss: 3.379005E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.407 | TFLOPs: 63.75 | +[default7]: iteration 2360/ 3814 | consumed samples: 1208320 | consumed tokens: 2474639360 | elapsed time per iteration (s): 6.04 | learning rate: 1.960E-04 | global batch size: 512 | lm loss: 3.393170E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.713 | TFLOPs: 63.98 | +[default7]: iteration 2361/ 3814 | consumed samples: 1208832 | consumed tokens: 2475687936 | elapsed time per iteration (s): 6.00 | learning rate: 1.957E-04 | global batch size: 512 | lm loss: 3.412357E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.310 | TFLOPs: 64.44 | +[default7]: iteration 2362/ 3814 | consumed samples: 1209344 | consumed tokens: 2476736512 | elapsed time per iteration (s): 6.07 | learning rate: 1.955E-04 | global batch size: 512 | lm loss: 3.396709E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.399 | TFLOPs: 63.75 | +[default7]: iteration 2363/ 3814 | consumed samples: 1209856 | consumed tokens: 2477785088 | elapsed time per iteration (s): 6.05 | learning rate: 1.953E-04 | global batch size: 512 | lm loss: 3.402439E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.574 | TFLOPs: 63.88 | +[default7]: iteration 2364/ 3814 | consumed samples: 1210368 | consumed tokens: 2478833664 | elapsed time per iteration (s): 6.09 | learning rate: 1.950E-04 | global batch size: 512 | lm loss: 3.403498E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.085 | TFLOPs: 63.51 | +[default7]: iteration 2365/ 3814 | consumed samples: 1210880 | consumed tokens: 2479882240 | elapsed time per iteration (s): 6.04 | learning rate: 1.948E-04 | global batch size: 512 | lm loss: 3.396815E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.738 | TFLOPs: 64.00 | +[default7]: iteration 2366/ 3814 | consumed samples: 1211392 | consumed tokens: 2480930816 | elapsed time per iteration (s): 6.03 | learning rate: 1.946E-04 | global batch size: 512 | lm loss: 3.408902E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.861 | TFLOPs: 64.10 | +[default7]: iteration 2367/ 3814 | consumed samples: 1211904 | consumed tokens: 2481979392 | elapsed time per iteration (s): 6.07 | learning rate: 1.944E-04 | global batch size: 512 | lm loss: 3.403154E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.349 | TFLOPs: 63.71 | +[default7]: iteration 2368/ 3814 | consumed samples: 1212416 | consumed tokens: 2483027968 | elapsed time per iteration (s): 6.06 | learning rate: 1.941E-04 | global batch size: 512 | lm loss: 3.374363E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.512 | TFLOPs: 63.83 | +[default7]: iteration 2369/ 3814 | consumed samples: 1212928 | consumed tokens: 2484076544 | elapsed time per iteration (s): 6.01 | learning rate: 1.939E-04 | global batch size: 512 | lm loss: 3.375181E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.177 | TFLOPs: 64.34 | +[default7]: iteration 2370/ 3814 | consumed samples: 1213440 | consumed tokens: 2485125120 | elapsed time per iteration (s): 5.99 | learning rate: 1.937E-04 | global batch size: 512 | lm loss: 3.392098E+00 | loss scale: 65536.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.458 | TFLOPs: 64.55 | +[default7]: iteration 2371/ 3814 | consumed samples: 1213952 | consumed tokens: 2486173696 | elapsed time per iteration (s): 6.01 | learning rate: 1.934E-04 | global batch size: 512 | lm loss: 3.379759E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.138 | TFLOPs: 64.31 | +[default7]: iteration 2372/ 3814 | consumed samples: 1214464 | consumed tokens: 2487222272 | elapsed time per iteration (s): 6.04 | learning rate: 1.932E-04 | global batch size: 512 | lm loss: 3.407109E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.829 | TFLOPs: 64.07 | +[default7]: iteration 2373/ 3814 | consumed samples: 1214976 | consumed tokens: 2488270848 | elapsed time per iteration (s): 6.05 | learning rate: 1.930E-04 | global batch size: 512 | lm loss: 3.421356E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.636 | TFLOPs: 63.93 | +[default7]: iteration 2374/ 3814 | consumed samples: 1215488 | consumed tokens: 2489319424 | elapsed time per iteration (s): 6.02 | learning rate: 1.928E-04 | global batch size: 512 | lm loss: 3.404402E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.014 | TFLOPs: 64.21 | +[default7]: iteration 2375/ 3814 | consumed samples: 1216000 | consumed tokens: 2490368000 | elapsed time per iteration (s): 6.08 | learning rate: 1.925E-04 | global batch size: 512 | lm loss: 3.409018E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.262 | TFLOPs: 63.64 | +[default7]: iteration 2376/ 3814 | consumed samples: 1216512 | consumed tokens: 2491416576 | elapsed time per iteration (s): 6.03 | learning rate: 1.923E-04 | global batch size: 512 | lm loss: 3.369232E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.976 | TFLOPs: 64.18 | +[default7]: iteration 2377/ 3814 | consumed samples: 1217024 | consumed tokens: 2492465152 | elapsed time per iteration (s): 6.06 | learning rate: 1.921E-04 | global batch size: 512 | lm loss: 3.420198E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.484 | TFLOPs: 63.81 | +[default7]: iteration 2378/ 3814 | consumed samples: 1217536 | consumed tokens: 2493513728 | elapsed time per iteration (s): 6.10 | learning rate: 1.919E-04 | global batch size: 512 | lm loss: 3.354158E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.982 | TFLOPs: 63.43 | +[default7]: iteration 2379/ 3814 | consumed samples: 1218048 | consumed tokens: 2494562304 | elapsed time per iteration (s): 6.06 | learning rate: 1.916E-04 | global batch size: 512 | lm loss: 3.395025E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.505 | TFLOPs: 63.83 | +[default7]: iteration 2380/ 3814 | consumed samples: 1218560 | consumed tokens: 2495610880 | elapsed time per iteration (s): 6.05 | learning rate: 1.914E-04 | global batch size: 512 | lm loss: 3.394775E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.596 | TFLOPs: 63.90 | +[default7]: iteration 2381/ 3814 | consumed samples: 1219072 | consumed tokens: 2496659456 | elapsed time per iteration (s): 6.04 | learning rate: 1.912E-04 | global batch size: 512 | lm loss: 3.398541E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.755 | TFLOPs: 64.02 | +[default7]: iteration 2382/ 3814 | consumed samples: 1219584 | consumed tokens: 2497708032 | elapsed time per iteration (s): 6.02 | learning rate: 1.909E-04 | global batch size: 512 | lm loss: 3.379616E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.024 | TFLOPs: 64.22 | +[default7]: iteration 2383/ 3814 | consumed samples: 1220096 | consumed tokens: 2498756608 | elapsed time per iteration (s): 6.00 | learning rate: 1.907E-04 | global batch size: 512 | lm loss: 3.364132E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.382 | TFLOPs: 64.49 | +[default7]: iteration 2384/ 3814 | consumed samples: 1220608 | consumed tokens: 2499805184 | elapsed time per iteration (s): 6.09 | learning rate: 1.905E-04 | global batch size: 512 | lm loss: 3.381921E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.094 | TFLOPs: 63.52 | +[default7]: iteration 2385/ 3814 | consumed samples: 1221120 | consumed tokens: 2500853760 | elapsed time per iteration (s): 6.00 | learning rate: 1.903E-04 | global batch size: 512 | lm loss: 3.402091E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.336 | TFLOPs: 64.46 | +[default7]: iteration 2386/ 3814 | consumed samples: 1221632 | consumed tokens: 2501902336 | elapsed time per iteration (s): 6.08 | learning rate: 1.900E-04 | global batch size: 512 | lm loss: 3.365310E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.197 | TFLOPs: 63.59 | +[default7]: iteration 2387/ 3814 | consumed samples: 1222144 | consumed tokens: 2502950912 | elapsed time per iteration (s): 6.05 | learning rate: 1.898E-04 | global batch size: 512 | lm loss: 3.382069E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.563 | TFLOPs: 63.87 | +[default7]: iteration 2388/ 3814 | consumed samples: 1222656 | consumed tokens: 2503999488 | elapsed time per iteration (s): 5.99 | learning rate: 1.896E-04 | global batch size: 512 | lm loss: 3.398874E+00 | loss scale: 65536.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.495 | TFLOPs: 64.58 | +[default7]: iteration 2389/ 3814 | consumed samples: 1223168 | consumed tokens: 2505048064 | elapsed time per iteration (s): 6.04 | learning rate: 1.893E-04 | global batch size: 512 | lm loss: 3.412761E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.725 | TFLOPs: 63.99 | +[default7]: iteration 2390/ 3814 | consumed samples: 1223680 | consumed tokens: 2506096640 | elapsed time per iteration (s): 6.07 | learning rate: 1.891E-04 | global batch size: 512 | lm loss: 3.407978E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.408 | TFLOPs: 63.75 | +[default7]: iteration 2391/ 3814 | consumed samples: 1224192 | consumed tokens: 2507145216 | elapsed time per iteration (s): 6.08 | learning rate: 1.889E-04 | global batch size: 512 | lm loss: 3.405705E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.191 | TFLOPs: 63.59 | +[default7]: iteration 2392/ 3814 | consumed samples: 1224704 | consumed tokens: 2508193792 | elapsed time per iteration (s): 6.05 | learning rate: 1.887E-04 | global batch size: 512 | lm loss: 3.393948E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.666 | TFLOPs: 63.95 | +[default7]: iteration 2393/ 3814 | consumed samples: 1225216 | consumed tokens: 2509242368 | elapsed time per iteration (s): 6.15 | learning rate: 1.884E-04 | global batch size: 512 | lm loss: 3.382204E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.232 | TFLOPs: 62.87 | +[default7]: iteration 2394/ 3814 | consumed samples: 1225728 | consumed tokens: 2510290944 | elapsed time per iteration (s): 6.06 | learning rate: 1.882E-04 | global batch size: 512 | lm loss: 3.398491E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.505 | TFLOPs: 63.83 | +[default7]: iteration 2395/ 3814 | consumed samples: 1226240 | consumed tokens: 2511339520 | elapsed time per iteration (s): 6.00 | learning rate: 1.880E-04 | global batch size: 512 | lm loss: 3.358392E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.321 | TFLOPs: 64.44 | +[default7]: iteration 2396/ 3814 | consumed samples: 1226752 | consumed tokens: 2512388096 | elapsed time per iteration (s): 6.00 | learning rate: 1.878E-04 | global batch size: 512 | lm loss: 3.431684E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.355 | TFLOPs: 64.47 | +[default7]: iteration 2397/ 3814 | consumed samples: 1227264 | consumed tokens: 2513436672 | elapsed time per iteration (s): 6.03 | learning rate: 1.875E-04 | global batch size: 512 | lm loss: 3.401563E+00 | loss scale: 65536.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.946 | TFLOPs: 64.16 | +[default7]: iteration 2398/ 3814 | consumed samples: 1227776 | consumed tokens: 2514485248 | elapsed time per iteration (s): 6.01 | learning rate: 1.873E-04 | global batch size: 512 | lm loss: 3.376223E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.171 | TFLOPs: 64.33 | +[default7]: iteration 2399/ 3814 | consumed samples: 1228288 | consumed tokens: 2515533824 | elapsed time per iteration (s): 5.99 | learning rate: 1.871E-04 | global batch size: 512 | lm loss: 3.386592E+00 | loss scale: 65536.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.454 | TFLOPs: 64.54 | +[default7]: iteration 2400/ 3814 | consumed samples: 1228800 | consumed tokens: 2516582400 | elapsed time per iteration (s): 6.01 | learning rate: 1.868E-04 | global batch size: 512 | lm loss: 3.377215E+00 | loss scale: 65536.0 | grad norm: 0.157 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.197 | TFLOPs: 64.35 | +[default7]: iteration 2401/ 3814 | consumed samples: 1229312 | consumed tokens: 2517630976 | elapsed time per iteration (s): 6.14 | learning rate: 1.866E-04 | global batch size: 512 | lm loss: 3.399655E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.454 | TFLOPs: 63.03 | +[default7]: iteration 2402/ 3814 | consumed samples: 1229824 | consumed tokens: 2518679552 | elapsed time per iteration (s): 6.05 | learning rate: 1.864E-04 | global batch size: 512 | lm loss: 3.404915E+00 | loss scale: 65536.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.583 | TFLOPs: 63.89 | +[default7]: iteration 2403/ 3814 | consumed samples: 1230336 | consumed tokens: 2519728128 | elapsed time per iteration (s): 6.10 | learning rate: 1.862E-04 | global batch size: 512 | lm loss: 3.405601E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.881 | TFLOPs: 63.36 | +[default7]: iteration 2404/ 3814 | consumed samples: 1230848 | consumed tokens: 2520776704 | elapsed time per iteration (s): 6.04 | learning rate: 1.859E-04 | global batch size: 512 | lm loss: 3.388454E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.795 | TFLOPs: 64.05 | +[default7]: iteration 2405/ 3814 | consumed samples: 1231360 | consumed tokens: 2521825280 | elapsed time per iteration (s): 6.09 | learning rate: 1.857E-04 | global batch size: 512 | lm loss: 3.399067E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.131 | TFLOPs: 63.55 | +[default7]: iteration 2406/ 3814 | consumed samples: 1231872 | consumed tokens: 2522873856 | elapsed time per iteration (s): 6.04 | learning rate: 1.855E-04 | global batch size: 512 | lm loss: 3.380478E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.740 | TFLOPs: 64.01 | +[default7]: iteration 2407/ 3814 | consumed samples: 1232384 | consumed tokens: 2523922432 | elapsed time per iteration (s): 5.93 | learning rate: 1.853E-04 | global batch size: 512 | lm loss: 3.373103E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.279 | TFLOPs: 65.17 | +[default7]: iteration 2408/ 3814 | consumed samples: 1232896 | consumed tokens: 2524971008 | elapsed time per iteration (s): 6.04 | learning rate: 1.850E-04 | global batch size: 512 | lm loss: 3.370500E+00 | loss scale: 65536.0 | grad norm: 0.156 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.809 | TFLOPs: 64.06 | +[default7]: iteration 2409/ 3814 | consumed samples: 1233408 | consumed tokens: 2526019584 | elapsed time per iteration (s): 6.00 | learning rate: 1.848E-04 | global batch size: 512 | lm loss: 3.357628E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.267 | TFLOPs: 64.40 | +[default7]: iteration 2410/ 3814 | consumed samples: 1233920 | consumed tokens: 2527068160 | elapsed time per iteration (s): 6.01 | learning rate: 1.846E-04 | global batch size: 512 | lm loss: 3.360716E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.173 | TFLOPs: 64.33 | +[default7]: iteration 2411/ 3814 | consumed samples: 1234432 | consumed tokens: 2528116736 | elapsed time per iteration (s): 6.02 | learning rate: 1.844E-04 | global batch size: 512 | lm loss: 3.409473E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.984 | TFLOPs: 64.19 | +[default7]: iteration 2412/ 3814 | consumed samples: 1234944 | consumed tokens: 2529165312 | elapsed time per iteration (s): 6.08 | learning rate: 1.841E-04 | global batch size: 512 | lm loss: 3.365472E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.178 | TFLOPs: 63.58 | +[default7]: iteration 2413/ 3814 | consumed samples: 1235456 | consumed tokens: 2530213888 | elapsed time per iteration (s): 6.03 | learning rate: 1.839E-04 | global batch size: 512 | lm loss: 3.372129E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.956 | TFLOPs: 64.17 | +[default7]: iteration 2414/ 3814 | consumed samples: 1235968 | consumed tokens: 2531262464 | elapsed time per iteration (s): 6.04 | learning rate: 1.837E-04 | global batch size: 512 | lm loss: 3.395643E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.730 | TFLOPs: 64.00 | +[default7]: iteration 2415/ 3814 | consumed samples: 1236480 | consumed tokens: 2532311040 | elapsed time per iteration (s): 6.03 | learning rate: 1.835E-04 | global batch size: 512 | lm loss: 3.397348E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.885 | TFLOPs: 64.11 | +[default7]: iteration 2416/ 3814 | consumed samples: 1236992 | consumed tokens: 2533359616 | elapsed time per iteration (s): 6.03 | learning rate: 1.832E-04 | global batch size: 512 | lm loss: 3.388521E+00 | loss scale: 65536.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.916 | TFLOPs: 64.14 | +[default7]: iteration 2417/ 3814 | consumed samples: 1237504 | consumed tokens: 2534408192 | elapsed time per iteration (s): 5.95 | learning rate: 1.830E-04 | global batch size: 512 | lm loss: 3.414818E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.050 | TFLOPs: 64.99 | +[default7]: iteration 2418/ 3814 | consumed samples: 1238016 | consumed tokens: 2535456768 | elapsed time per iteration (s): 6.03 | learning rate: 1.828E-04 | global batch size: 512 | lm loss: 3.377215E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.969 | TFLOPs: 64.18 | +[default7]: iteration 2419/ 3814 | consumed samples: 1238528 | consumed tokens: 2536505344 | elapsed time per iteration (s): 6.00 | learning rate: 1.826E-04 | global batch size: 512 | lm loss: 3.351331E+00 | loss scale: 65536.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.313 | TFLOPs: 64.44 | +[default7]: iteration 2420/ 3814 | consumed samples: 1239040 | consumed tokens: 2537553920 | elapsed time per iteration (s): 5.99 | learning rate: 1.823E-04 | global batch size: 512 | lm loss: 3.377755E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.426 | TFLOPs: 64.52 | +[default7]: iteration 2421/ 3814 | consumed samples: 1239552 | consumed tokens: 2538602496 | elapsed time per iteration (s): 6.05 | learning rate: 1.821E-04 | global batch size: 512 | lm loss: 3.364712E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.661 | TFLOPs: 63.95 | +[default7]: iteration 2422/ 3814 | consumed samples: 1240064 | consumed tokens: 2539651072 | elapsed time per iteration (s): 6.02 | learning rate: 1.819E-04 | global batch size: 512 | lm loss: 3.383150E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.991 | TFLOPs: 64.19 | +[default7]: iteration 2423/ 3814 | consumed samples: 1240576 | consumed tokens: 2540699648 | elapsed time per iteration (s): 6.04 | learning rate: 1.817E-04 | global batch size: 512 | lm loss: 3.368822E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.829 | TFLOPs: 64.07 | +[default7]: iteration 2424/ 3814 | consumed samples: 1241088 | consumed tokens: 2541748224 | elapsed time per iteration (s): 6.02 | learning rate: 1.814E-04 | global batch size: 512 | lm loss: 3.365783E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.059 | TFLOPs: 64.25 | +[default7]: iteration 2425/ 3814 | consumed samples: 1241600 | consumed tokens: 2542796800 | elapsed time per iteration (s): 5.92 | learning rate: 1.812E-04 | global batch size: 512 | lm loss: 3.377698E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.518 | TFLOPs: 65.35 | +[default7]: iteration 2426/ 3814 | consumed samples: 1242112 | consumed tokens: 2543845376 | elapsed time per iteration (s): 6.01 | learning rate: 1.810E-04 | global batch size: 512 | lm loss: 3.389766E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.238 | TFLOPs: 64.38 | +[default7]: iteration 2427/ 3814 | consumed samples: 1242624 | consumed tokens: 2544893952 | elapsed time per iteration (s): 5.99 | learning rate: 1.808E-04 | global batch size: 512 | lm loss: 3.365698E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.507 | TFLOPs: 64.58 | +[default7]: iteration 2428/ 3814 | consumed samples: 1243136 | consumed tokens: 2545942528 | elapsed time per iteration (s): 5.88 | learning rate: 1.805E-04 | global batch size: 512 | lm loss: 3.386142E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.051 | TFLOPs: 65.75 | +[default7]: iteration 2429/ 3814 | consumed samples: 1243648 | consumed tokens: 2546991104 | elapsed time per iteration (s): 6.04 | learning rate: 1.803E-04 | global batch size: 512 | lm loss: 3.392616E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.801 | TFLOPs: 64.05 | +[default7]: iteration 2430/ 3814 | consumed samples: 1244160 | consumed tokens: 2548039680 | elapsed time per iteration (s): 6.02 | learning rate: 1.801E-04 | global batch size: 512 | lm loss: 3.341049E+00 | loss scale: 65536.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.043 | TFLOPs: 64.23 | +[default7]: iteration 2431/ 3814 | consumed samples: 1244672 | consumed tokens: 2549088256 | elapsed time per iteration (s): 6.04 | learning rate: 1.799E-04 | global batch size: 512 | lm loss: 3.378679E+00 | loss scale: 65536.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.820 | TFLOPs: 64.07 | +[default7]: iteration 2432/ 3814 | consumed samples: 1245184 | consumed tokens: 2550136832 | elapsed time per iteration (s): 6.06 | learning rate: 1.796E-04 | global batch size: 512 | lm loss: 3.400455E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.533 | TFLOPs: 63.85 | +[default7]: iteration 2433/ 3814 | consumed samples: 1245696 | consumed tokens: 2551185408 | elapsed time per iteration (s): 6.02 | learning rate: 1.794E-04 | global batch size: 512 | lm loss: 3.383093E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.028 | TFLOPs: 64.22 | +[default7]: iteration 2434/ 3814 | consumed samples: 1246208 | consumed tokens: 2552233984 | elapsed time per iteration (s): 6.04 | learning rate: 1.792E-04 | global batch size: 512 | lm loss: 3.378836E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.822 | TFLOPs: 64.07 | +[default7]: iteration 2435/ 3814 | consumed samples: 1246720 | consumed tokens: 2553282560 | elapsed time per iteration (s): 5.98 | learning rate: 1.790E-04 | global batch size: 512 | lm loss: 3.380634E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.605 | TFLOPs: 64.66 | +[default7]: iteration 2436/ 3814 | consumed samples: 1247232 | consumed tokens: 2554331136 | elapsed time per iteration (s): 5.99 | learning rate: 1.787E-04 | global batch size: 512 | lm loss: 3.392524E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.414 | TFLOPs: 64.51 | +[default7]: iteration 2437/ 3814 | consumed samples: 1247744 | consumed tokens: 2555379712 | elapsed time per iteration (s): 5.92 | learning rate: 1.785E-04 | global batch size: 512 | lm loss: 3.375437E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.441 | TFLOPs: 65.29 | +[default7]: iteration 2438/ 3814 | consumed samples: 1248256 | consumed tokens: 2556428288 | elapsed time per iteration (s): 5.99 | learning rate: 1.783E-04 | global batch size: 512 | lm loss: 3.379205E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.511 | TFLOPs: 64.59 | +[default7]: iteration 2439/ 3814 | consumed samples: 1248768 | consumed tokens: 2557476864 | elapsed time per iteration (s): 5.95 | learning rate: 1.781E-04 | global batch size: 512 | lm loss: 3.377296E+00 | loss scale: 65536.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.089 | TFLOPs: 65.02 | +[default7]: iteration 2440/ 3814 | consumed samples: 1249280 | consumed tokens: 2558525440 | elapsed time per iteration (s): 6.05 | learning rate: 1.778E-04 | global batch size: 512 | lm loss: 3.328726E+00 | loss scale: 65536.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.681 | TFLOPs: 63.96 | +[default7]: iteration 2441/ 3814 | consumed samples: 1249792 | consumed tokens: 2559574016 | elapsed time per iteration (s): 5.99 | learning rate: 1.776E-04 | global batch size: 512 | lm loss: 3.379423E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.488 | TFLOPs: 64.57 | +[default7]: iteration 2442/ 3814 | consumed samples: 1250304 | consumed tokens: 2560622592 | elapsed time per iteration (s): 5.95 | learning rate: 1.774E-04 | global batch size: 512 | lm loss: 3.367564E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.032 | TFLOPs: 64.98 | +[default7]: iteration 2443/ 3814 | consumed samples: 1250816 | consumed tokens: 2561671168 | elapsed time per iteration (s): 5.96 | learning rate: 1.772E-04 | global batch size: 512 | lm loss: 3.386340E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.902 | TFLOPs: 64.88 | +[default7]: iteration 2444/ 3814 | consumed samples: 1251328 | consumed tokens: 2562719744 | elapsed time per iteration (s): 5.99 | learning rate: 1.769E-04 | global batch size: 512 | lm loss: 3.348395E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.448 | TFLOPs: 64.54 | +[default7]: iteration 2445/ 3814 | consumed samples: 1251840 | consumed tokens: 2563768320 | elapsed time per iteration (s): 5.96 | learning rate: 1.767E-04 | global batch size: 512 | lm loss: 3.382624E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.975 | TFLOPs: 64.94 | +[default7]: iteration 2446/ 3814 | consumed samples: 1252352 | consumed tokens: 2564816896 | elapsed time per iteration (s): 6.08 | learning rate: 1.765E-04 | global batch size: 512 | lm loss: 3.384765E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.194 | TFLOPs: 63.59 | +[default7]: iteration 2447/ 3814 | consumed samples: 1252864 | consumed tokens: 2565865472 | elapsed time per iteration (s): 5.97 | learning rate: 1.763E-04 | global batch size: 512 | lm loss: 3.349558E+00 | loss scale: 65536.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.825 | TFLOPs: 64.82 | +[default7]: iteration 2448/ 3814 | consumed samples: 1253376 | consumed tokens: 2566914048 | elapsed time per iteration (s): 6.01 | learning rate: 1.760E-04 | global batch size: 512 | lm loss: 3.384611E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.247 | TFLOPs: 64.39 | +[default7]: iteration 2449/ 3814 | consumed samples: 1253888 | consumed tokens: 2567962624 | elapsed time per iteration (s): 6.03 | learning rate: 1.758E-04 | global batch size: 512 | lm loss: 3.357509E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.974 | TFLOPs: 64.18 | +[default7]: iteration 2450/ 3814 | consumed samples: 1254400 | consumed tokens: 2569011200 | elapsed time per iteration (s): 5.98 | learning rate: 1.756E-04 | global batch size: 512 | lm loss: 3.370709E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.574 | TFLOPs: 64.63 | +[default7]: iteration 2451/ 3814 | consumed samples: 1254912 | consumed tokens: 2570059776 | elapsed time per iteration (s): 5.94 | learning rate: 1.754E-04 | global batch size: 512 | lm loss: 3.352955E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.196 | TFLOPs: 65.10 | +[default7]: iteration 2452/ 3814 | consumed samples: 1255424 | consumed tokens: 2571108352 | elapsed time per iteration (s): 5.98 | learning rate: 1.751E-04 | global batch size: 512 | lm loss: 3.386047E+00 | loss scale: 65536.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.625 | TFLOPs: 64.67 | +[default7]: iteration 2453/ 3814 | consumed samples: 1255936 | consumed tokens: 2572156928 | elapsed time per iteration (s): 6.03 | learning rate: 1.749E-04 | global batch size: 512 | lm loss: 3.395156E+00 | loss scale: 65536.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.891 | TFLOPs: 64.12 | +[default7]: iteration 2454/ 3814 | consumed samples: 1256448 | consumed tokens: 2573205504 | elapsed time per iteration (s): 5.97 | learning rate: 1.747E-04 | global batch size: 512 | lm loss: 3.367734E+00 | loss scale: 65536.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.762 | TFLOPs: 64.78 | +[default7]: iteration 2455/ 3814 | consumed samples: 1256960 | consumed tokens: 2574254080 | elapsed time per iteration (s): 5.98 | learning rate: 1.745E-04 | global batch size: 512 | lm loss: 3.392988E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.569 | TFLOPs: 64.63 | +[default7]: iteration 2456/ 3814 | consumed samples: 1257472 | consumed tokens: 2575302656 | elapsed time per iteration (s): 5.99 | learning rate: 1.743E-04 | global batch size: 512 | lm loss: 3.364937E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.498 | TFLOPs: 64.58 | +[default7]: iteration 2457/ 3814 | consumed samples: 1257984 | consumed tokens: 2576351232 | elapsed time per iteration (s): 6.05 | learning rate: 1.740E-04 | global batch size: 512 | lm loss: 3.390751E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.642 | TFLOPs: 63.93 | +[default7]: iteration 2458/ 3814 | consumed samples: 1258496 | consumed tokens: 2577399808 | elapsed time per iteration (s): 6.00 | learning rate: 1.738E-04 | global batch size: 512 | lm loss: 3.347832E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.336 | TFLOPs: 64.45 | +[default7]: iteration 2459/ 3814 | consumed samples: 1259008 | consumed tokens: 2578448384 | elapsed time per iteration (s): 6.03 | learning rate: 1.736E-04 | global batch size: 512 | lm loss: 3.379477E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.871 | TFLOPs: 64.10 | +[default7]: iteration 2460/ 3814 | consumed samples: 1259520 | consumed tokens: 2579496960 | elapsed time per iteration (s): 5.92 | learning rate: 1.734E-04 | global batch size: 512 | lm loss: 3.356275E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.539 | TFLOPs: 65.36 | +[default7]: iteration 2461/ 3814 | consumed samples: 1260032 | consumed tokens: 2580545536 | elapsed time per iteration (s): 5.98 | learning rate: 1.731E-04 | global batch size: 512 | lm loss: 3.387923E+00 | loss scale: 65536.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.597 | TFLOPs: 64.65 | +[default7]: iteration 2462/ 3814 | consumed samples: 1260544 | consumed tokens: 2581594112 | elapsed time per iteration (s): 6.05 | learning rate: 1.729E-04 | global batch size: 512 | lm loss: 3.365561E+00 | loss scale: 65536.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.579 | TFLOPs: 63.88 | +[default7]: iteration 2463/ 3814 | consumed samples: 1261056 | consumed tokens: 2582642688 | elapsed time per iteration (s): 5.98 | learning rate: 1.727E-04 | global batch size: 512 | lm loss: 3.352565E+00 | loss scale: 65536.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.560 | TFLOPs: 64.62 | +[default7]: iteration 2464/ 3814 | consumed samples: 1261568 | consumed tokens: 2583691264 | elapsed time per iteration (s): 6.04 | learning rate: 1.725E-04 | global batch size: 512 | lm loss: 3.376874E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.787 | TFLOPs: 64.04 | +[default7]: iteration 2465/ 3814 | consumed samples: 1262080 | consumed tokens: 2584739840 | elapsed time per iteration (s): 6.04 | learning rate: 1.722E-04 | global batch size: 512 | lm loss: 3.381925E+00 | loss scale: 65536.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.732 | TFLOPs: 64.00 | +[default7]: iteration 2466/ 3814 | consumed samples: 1262592 | consumed tokens: 2585788416 | elapsed time per iteration (s): 6.01 | learning rate: 1.720E-04 | global batch size: 512 | lm loss: 3.363701E+00 | loss scale: 65536.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.261 | TFLOPs: 64.40 | +[default7]: iteration 2467/ 3814 | consumed samples: 1263104 | consumed tokens: 2586836992 | elapsed time per iteration (s): 6.04 | learning rate: 1.718E-04 | global batch size: 512 | lm loss: 3.363640E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.752 | TFLOPs: 64.01 | +[default7]: iteration 2468/ 3814 | consumed samples: 1263616 | consumed tokens: 2587885568 | elapsed time per iteration (s): 6.00 | learning rate: 1.716E-04 | global batch size: 512 | lm loss: 3.374779E+00 | loss scale: 65536.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.303 | TFLOPs: 64.43 | +[default7]: iteration 2469/ 3814 | consumed samples: 1264128 | consumed tokens: 2588934144 | elapsed time per iteration (s): 5.71 | learning rate: 1.714E-04 | global batch size: 512 | lm loss: 3.378115E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.644 | TFLOPs: 67.71 | +[default7]: iteration 2470/ 3814 | consumed samples: 1264640 | consumed tokens: 2589982720 | elapsed time per iteration (s): 6.01 | learning rate: 1.711E-04 | global batch size: 512 | lm loss: 3.404579E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.220 | TFLOPs: 64.37 | +[default7]: iteration 2471/ 3814 | consumed samples: 1265152 | consumed tokens: 2591031296 | elapsed time per iteration (s): 6.03 | learning rate: 1.709E-04 | global batch size: 512 | lm loss: 3.382266E+00 | loss scale: 65536.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.926 | TFLOPs: 64.15 | +[default7]: iteration 2472/ 3814 | consumed samples: 1265664 | consumed tokens: 2592079872 | elapsed time per iteration (s): 5.99 | learning rate: 1.707E-04 | global batch size: 512 | lm loss: 3.375244E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.429 | TFLOPs: 64.53 | +[default7]: iteration 2473/ 3814 | consumed samples: 1266176 | consumed tokens: 2593128448 | elapsed time per iteration (s): 6.03 | learning rate: 1.705E-04 | global batch size: 512 | lm loss: 3.359271E+00 | loss scale: 65536.0 | grad norm: 0.142 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.906 | TFLOPs: 64.13 | +[default7]: iteration 2474/ 3814 | consumed samples: 1266688 | consumed tokens: 2594177024 | elapsed time per iteration (s): 5.94 | learning rate: 1.702E-04 | global batch size: 512 | lm loss: 3.346443E+00 | loss scale: 65536.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.153 | TFLOPs: 65.07 | +[default7]: iteration 2475/ 3814 | consumed samples: 1267200 | consumed tokens: 2595225600 | elapsed time per iteration (s): 6.05 | learning rate: 1.700E-04 | global batch size: 512 | lm loss: 3.377629E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.626 | TFLOPs: 63.92 | +[default7]: iteration 2476/ 3814 | consumed samples: 1267712 | consumed tokens: 2596274176 | elapsed time per iteration (s): 5.97 | learning rate: 1.698E-04 | global batch size: 512 | lm loss: 3.362679E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.737 | TFLOPs: 64.76 | +[default7]: iteration 2477/ 3814 | consumed samples: 1268224 | consumed tokens: 2597322752 | elapsed time per iteration (s): 6.03 | learning rate: 1.696E-04 | global batch size: 512 | lm loss: 3.381497E+00 | loss scale: 65536.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.939 | TFLOPs: 64.16 | +[default7]: iteration 2478/ 3814 | consumed samples: 1268736 | consumed tokens: 2598371328 | elapsed time per iteration (s): 5.91 | learning rate: 1.694E-04 | global batch size: 512 | lm loss: 3.388255E+00 | loss scale: 65536.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.667 | TFLOPs: 65.46 | +[default7]: iteration 2479/ 3814 | consumed samples: 1269248 | consumed tokens: 2599419904 | elapsed time per iteration (s): 5.96 | learning rate: 1.691E-04 | global batch size: 512 | lm loss: 3.370900E+00 | loss scale: 65536.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.851 | TFLOPs: 64.84 | +[default7]: iteration 2480/ 3814 | consumed samples: 1269760 | consumed tokens: 2600468480 | elapsed time per iteration (s): 6.02 | learning rate: 1.689E-04 | global batch size: 512 | lm loss: 3.373752E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.030 | TFLOPs: 64.22 | +[default7]: iteration 2481/ 3814 | consumed samples: 1270272 | consumed tokens: 2601517056 | elapsed time per iteration (s): 6.02 | learning rate: 1.687E-04 | global batch size: 512 | lm loss: 3.337005E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.985 | TFLOPs: 64.19 | +[default7]: iteration 2482/ 3814 | consumed samples: 1270784 | consumed tokens: 2602565632 | elapsed time per iteration (s): 5.98 | learning rate: 1.685E-04 | global batch size: 512 | lm loss: 3.344729E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.645 | TFLOPs: 64.69 | +[default7]: iteration 2483/ 3814 | consumed samples: 1271296 | consumed tokens: 2603614208 | elapsed time per iteration (s): 5.94 | learning rate: 1.683E-04 | global batch size: 512 | lm loss: 3.374915E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.127 | TFLOPs: 65.05 | +[default7]: iteration 2484/ 3814 | consumed samples: 1271808 | consumed tokens: 2604662784 | elapsed time per iteration (s): 5.96 | learning rate: 1.680E-04 | global batch size: 512 | lm loss: 3.366841E+00 | loss scale: 65536.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.896 | TFLOPs: 64.88 | +[default7]: iteration 2485/ 3814 | consumed samples: 1272320 | consumed tokens: 2605711360 | elapsed time per iteration (s): 5.97 | learning rate: 1.678E-04 | global batch size: 512 | lm loss: 3.354859E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.823 | TFLOPs: 64.82 | +[default7]: iteration 2486/ 3814 | consumed samples: 1272832 | consumed tokens: 2606759936 | elapsed time per iteration (s): 6.01 | learning rate: 1.676E-04 | global batch size: 512 | lm loss: 3.350540E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.219 | TFLOPs: 64.37 | +[default7]: iteration 2487/ 3814 | consumed samples: 1273344 | consumed tokens: 2607808512 | elapsed time per iteration (s): 5.99 | learning rate: 1.674E-04 | global batch size: 512 | lm loss: 3.347628E+00 | loss scale: 65536.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.473 | TFLOPs: 64.56 | +[default7]: iteration 2488/ 3814 | consumed samples: 1273856 | consumed tokens: 2608857088 | elapsed time per iteration (s): 5.75 | learning rate: 1.672E-04 | global batch size: 512 | lm loss: 3.371815E+00 | loss scale: 65536.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.074 | TFLOPs: 67.28 | +[default7]: iteration 2489/ 3814 | consumed samples: 1274368 | consumed tokens: 2609905664 | elapsed time per iteration (s): 6.03 | learning rate: 1.669E-04 | global batch size: 512 | lm loss: 3.352943E+00 | loss scale: 65536.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.950 | TFLOPs: 64.16 | +[default7]: iteration 2490/ 3814 | consumed samples: 1274880 | consumed tokens: 2610954240 | elapsed time per iteration (s): 6.05 | learning rate: 1.667E-04 | global batch size: 512 | lm loss: 3.381653E+00 | loss scale: 65536.0 | grad norm: 0.141 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.661 | TFLOPs: 63.95 | +[default7]: iteration 2491/ 3814 | consumed samples: 1275392 | consumed tokens: 2612002816 | elapsed time per iteration (s): 6.02 | learning rate: 1.665E-04 | global batch size: 512 | lm loss: 3.330920E+00 | loss scale: 65536.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.990 | TFLOPs: 64.19 | +[default7]: iteration 2492/ 3814 | consumed samples: 1275904 | consumed tokens: 2613051392 | elapsed time per iteration (s): 5.99 | learning rate: 1.663E-04 | global batch size: 512 | lm loss: 3.365413E+00 | loss scale: 65536.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.490 | TFLOPs: 64.57 | +[default7]: iteration 2493/ 3814 | consumed samples: 1276416 | consumed tokens: 2614099968 | elapsed time per iteration (s): 5.97 | learning rate: 1.660E-04 | global batch size: 512 | lm loss: 3.399924E+00 | loss scale: 65536.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.741 | TFLOPs: 64.76 | +[default7]: iteration 2494/ 3814 | consumed samples: 1276928 | consumed tokens: 2615148544 | elapsed time per iteration (s): 5.83 | learning rate: 1.658E-04 | global batch size: 512 | lm loss: 3.365990E+00 | loss scale: 65536.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.870 | TFLOPs: 66.37 | +[default7]: iteration 2495/ 3814 | consumed samples: 1277440 | consumed tokens: 2616197120 | elapsed time per iteration (s): 6.02 | learning rate: 1.656E-04 | global batch size: 512 | lm loss: 3.376509E+00 | loss scale: 65536.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.033 | TFLOPs: 64.23 | +[default7]: iteration 2496/ 3814 | consumed samples: 1277952 | consumed tokens: 2617245696 | elapsed time per iteration (s): 6.04 | learning rate: 1.654E-04 | global batch size: 512 | lm loss: 3.365582E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.756 | TFLOPs: 64.02 | +[default7]: iteration 2497/ 3814 | consumed samples: 1278464 | consumed tokens: 2618294272 | elapsed time per iteration (s): 5.97 | learning rate: 1.652E-04 | global batch size: 512 | lm loss: 3.366794E+00 | loss scale: 65536.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.732 | TFLOPs: 64.75 | +[default7]: iteration 2498/ 3814 | consumed samples: 1278976 | consumed tokens: 2619342848 | elapsed time per iteration (s): 6.01 | learning rate: 1.649E-04 | global batch size: 512 | lm loss: 3.358348E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.222 | TFLOPs: 64.37 | +[default7]: iteration 2499/ 3814 | consumed samples: 1279488 | consumed tokens: 2620391424 | elapsed time per iteration (s): 6.00 | learning rate: 1.647E-04 | global batch size: 512 | lm loss: 3.353419E+00 | loss scale: 65536.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.283 | TFLOPs: 64.42 | +[default7]: iteration 2500/ 3814 | consumed samples: 1280000 | consumed tokens: 2621440000 | elapsed time per iteration (s): 5.94 | learning rate: 1.645E-04 | global batch size: 512 | lm loss: 3.365085E+00 | loss scale: 131072.0 | grad norm: 0.056 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.154 | TFLOPs: 65.07 | +[default0]:saving checkpoint at iteration 2500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 11:43:20,568] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2500 is begin to save! +[default0]:[2023-02-16 11:43:20,589] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:20,589] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:20,756] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:20,757] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:20,755] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:20,755] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:20,817] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:20,818] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:20,813] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:20,813] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:20,876] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:20,877] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:20,934] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:20,935] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:20,868] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:20,869] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:20,923] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:20,923] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,000] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,001] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:20,986] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:20,987] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,055] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,056] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,067] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,067] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:21,127] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,128] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,114] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,115] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,186] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:21,241] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,242] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,174] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,174] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,229] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,308] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,291] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,291] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,351] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:21,430] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,406] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,407] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:21,555] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,556] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,477] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,477] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,540] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,541] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,618] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,596] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,596] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,654] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,655] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,674] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,674] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:21,729] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,729] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,710] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,711] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,764] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,765] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,789] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,789] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:21,847] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,848] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,822] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,909] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,910] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:21,884] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,884] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:21,949] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:21,949] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:21,975] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:21,975] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:22,042] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,043] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,014] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,015] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:22,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,109] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,069] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,069] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:22,133] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,134] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:22,172] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,172] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:22,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,230] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,196] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:22,251] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,252] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:22,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,287] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:22,345] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,346] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,309] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:22,364] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,364] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:22,400] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,401] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,423] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:22,464] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,465] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:22,523] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,523] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,478] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,479] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:22,532] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,533] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_01-model_states.pt... +[default0]:[2023-02-16 11:43:22,581] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,581] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:22,639] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,639] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_00-model_states.pt... +[default1]:[2023-02-16 11:43:22,591] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,591] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:22,646] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,647] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 11:43:22,647] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 11:43:22,649] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_01_model_states.pt +[default1]:[2023-02-16 11:43:22,649] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 11:43:22,651] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_01_model_states.pt. +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:43:22,694] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,694] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 11:43:22,695] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 11:43:22,696] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_00_model_states.pt +[default0]:[2023-02-16 11:43:22,696] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 11:43:22,698] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 11:43:22,731] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 11:43:23,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,204] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,204] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,238] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,238] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,239] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,239] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,239] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,204] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,205] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,205] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,284] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,285] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,273] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,273] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,273] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,322] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,322] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,322] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,287] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,288] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,320] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,320] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,320] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,288] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,303] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,303] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,303] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,296] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,296] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,296] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,305] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,305] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,351] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,353] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,353] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,327] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,327] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,328] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,326] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,326] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,326] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,339] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,339] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,339] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,316] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,316] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,316] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,288] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,288] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,288] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,348] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,287] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,287] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,355] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,355] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,355] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,389] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,389] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,319] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,319] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,319] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,361] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,361] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,361] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,305] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,305] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,306] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,350] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,350] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,350] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,396] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,396] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,396] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,404] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,404] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,404] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,360] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,360] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,348] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,348] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,390] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,390] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,403] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,403] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,403] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,335] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,335] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,407] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,407] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,407] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,395] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,408] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,408] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,408] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,356] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,357] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,357] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,389] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,389] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,390] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,359] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,359] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,359] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,434] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,434] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,434] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,433] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,395] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,395] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,395] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,431] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,431] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,505] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,505] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,505] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,461] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,461] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,461] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,457] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,457] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,457] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,454] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,454] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,454] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,433] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,433] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,433] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default1]:[2023-02-16 11:43:23,467] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 11:43:23,468] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 11:43:23,468] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,449] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,449] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,487] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,494] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,494] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,494] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,502] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,502] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,502] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default3]:[2023-02-16 11:43:23,480] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 11:43:23,480] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 11:43:23,480] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default0]:[2023-02-16 11:43:23,527] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 11:43:23,527] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 11:43:23,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default4]:[2023-02-16 11:43:23,542] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 11:43:23,542] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 11:43:23,543] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,521] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,522] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,522] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,522] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default2]:[2023-02-16 11:43:23,580] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 11:43:23,580] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 11:43:23,580] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default5]:[2023-02-16 11:43:23,561] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 11:43:23,561] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 11:43:23,561] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:[2023-02-16 11:43:23,578] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,578] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,578] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]:time (ms) | save-checkpoint: 3169.14 +[default0]: successfully saved checkpoint at iteration 2500 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]:[2023-02-16 11:43:23,725] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 11:43:23,725] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 11:43:23,725] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default6]:[2023-02-16 11:43:23,732] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 11:43:23,732] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2500/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 11:43:23,732] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2500 is ready now! +[default7]: iteration 2501/ 3814 | consumed samples: 1280512 | consumed tokens: 2622488576 | elapsed time per iteration (s): 9.17 | learning rate: 1.643E-04 | global batch size: 512 | lm loss: 3.369062E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 55.844 | TFLOPs: 42.18 | +[default7]: iteration 2502/ 3814 | consumed samples: 1281024 | consumed tokens: 2623537152 | elapsed time per iteration (s): 5.95 | learning rate: 1.641E-04 | global batch size: 512 | lm loss: 3.364499E+00 | loss scale: 131072.0 | grad norm: 0.145 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.010 | TFLOPs: 64.96 | +[default7]: iteration 2503/ 3814 | consumed samples: 1281536 | consumed tokens: 2624585728 | elapsed time per iteration (s): 6.02 | learning rate: 1.639E-04 | global batch size: 512 | lm loss: 3.378466E+00 | loss scale: 131072.0 | grad norm: 0.144 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.026 | TFLOPs: 64.22 | +[default7]: iteration 2504/ 3814 | consumed samples: 1282048 | consumed tokens: 2625634304 | elapsed time per iteration (s): 5.90 | learning rate: 1.636E-04 | global batch size: 512 | lm loss: 3.349239E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.743 | TFLOPs: 65.52 | +[default7]: iteration 2505/ 3814 | consumed samples: 1282560 | consumed tokens: 2626682880 | elapsed time per iteration (s): 6.02 | learning rate: 1.634E-04 | global batch size: 512 | lm loss: 3.356394E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.980 | TFLOPs: 64.19 | +[default7]: iteration 2506/ 3814 | consumed samples: 1283072 | consumed tokens: 2627731456 | elapsed time per iteration (s): 5.96 | learning rate: 1.632E-04 | global batch size: 512 | lm loss: 3.374014E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.965 | TFLOPs: 64.93 | +[default7]: iteration 2507/ 3814 | consumed samples: 1283584 | consumed tokens: 2628780032 | elapsed time per iteration (s): 6.01 | learning rate: 1.630E-04 | global batch size: 512 | lm loss: 3.342570E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.186 | TFLOPs: 64.34 | +[default7]: iteration 2508/ 3814 | consumed samples: 1284096 | consumed tokens: 2629828608 | elapsed time per iteration (s): 6.00 | learning rate: 1.628E-04 | global batch size: 512 | lm loss: 3.377920E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.379 | TFLOPs: 64.49 | +[default7]: iteration 2509/ 3814 | consumed samples: 1284608 | consumed tokens: 2630877184 | elapsed time per iteration (s): 6.00 | learning rate: 1.625E-04 | global batch size: 512 | lm loss: 3.351049E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.285 | TFLOPs: 64.42 | +[default7]: iteration 2510/ 3814 | consumed samples: 1285120 | consumed tokens: 2631925760 | elapsed time per iteration (s): 5.99 | learning rate: 1.623E-04 | global batch size: 512 | lm loss: 3.321615E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.485 | TFLOPs: 64.57 | +[default7]: iteration 2511/ 3814 | consumed samples: 1285632 | consumed tokens: 2632974336 | elapsed time per iteration (s): 6.03 | learning rate: 1.621E-04 | global batch size: 512 | lm loss: 3.358578E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.897 | TFLOPs: 64.12 | +[default7]: iteration 2512/ 3814 | consumed samples: 1286144 | consumed tokens: 2634022912 | elapsed time per iteration (s): 5.97 | learning rate: 1.619E-04 | global batch size: 512 | lm loss: 3.357952E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.809 | TFLOPs: 64.81 | +[default7]: iteration 2513/ 3814 | consumed samples: 1286656 | consumed tokens: 2635071488 | elapsed time per iteration (s): 5.95 | learning rate: 1.617E-04 | global batch size: 512 | lm loss: 3.376192E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.010 | TFLOPs: 64.96 | +[default7]: iteration 2514/ 3814 | consumed samples: 1287168 | consumed tokens: 2636120064 | elapsed time per iteration (s): 5.98 | learning rate: 1.614E-04 | global batch size: 512 | lm loss: 3.373087E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.641 | TFLOPs: 64.69 | +[default7]: iteration 2515/ 3814 | consumed samples: 1287680 | consumed tokens: 2637168640 | elapsed time per iteration (s): 6.05 | learning rate: 1.612E-04 | global batch size: 512 | lm loss: 3.372983E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.578 | TFLOPs: 63.88 | +[default7]: iteration 2516/ 3814 | consumed samples: 1288192 | consumed tokens: 2638217216 | elapsed time per iteration (s): 6.02 | learning rate: 1.610E-04 | global batch size: 512 | lm loss: 3.351169E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.027 | TFLOPs: 64.22 | +[default7]: iteration 2517/ 3814 | consumed samples: 1288704 | consumed tokens: 2639265792 | elapsed time per iteration (s): 6.02 | learning rate: 1.608E-04 | global batch size: 512 | lm loss: 3.347400E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.018 | TFLOPs: 64.21 | +[default7]: iteration 2518/ 3814 | consumed samples: 1289216 | consumed tokens: 2640314368 | elapsed time per iteration (s): 6.01 | learning rate: 1.606E-04 | global batch size: 512 | lm loss: 3.377632E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.258 | TFLOPs: 64.40 | +[default7]: iteration 2519/ 3814 | consumed samples: 1289728 | consumed tokens: 2641362944 | elapsed time per iteration (s): 6.04 | learning rate: 1.603E-04 | global batch size: 512 | lm loss: 3.346385E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.804 | TFLOPs: 64.05 | +[default7]: iteration 2520/ 3814 | consumed samples: 1290240 | consumed tokens: 2642411520 | elapsed time per iteration (s): 5.98 | learning rate: 1.601E-04 | global batch size: 512 | lm loss: 3.372895E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.585 | TFLOPs: 64.64 | +[default7]: iteration 2521/ 3814 | consumed samples: 1290752 | consumed tokens: 2643460096 | elapsed time per iteration (s): 6.04 | learning rate: 1.599E-04 | global batch size: 512 | lm loss: 3.360658E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.728 | TFLOPs: 64.00 | +[default7]: iteration 2522/ 3814 | consumed samples: 1291264 | consumed tokens: 2644508672 | elapsed time per iteration (s): 5.98 | learning rate: 1.597E-04 | global batch size: 512 | lm loss: 3.368371E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.631 | TFLOPs: 64.68 | +[default7]: iteration 2523/ 3814 | consumed samples: 1291776 | consumed tokens: 2645557248 | elapsed time per iteration (s): 6.05 | learning rate: 1.595E-04 | global batch size: 512 | lm loss: 3.390287E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.612 | TFLOPs: 63.91 | +[default7]: iteration 2524/ 3814 | consumed samples: 1292288 | consumed tokens: 2646605824 | elapsed time per iteration (s): 5.93 | learning rate: 1.593E-04 | global batch size: 512 | lm loss: 3.387284E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.358 | TFLOPs: 65.23 | +[default7]: iteration 2525/ 3814 | consumed samples: 1292800 | consumed tokens: 2647654400 | elapsed time per iteration (s): 5.95 | learning rate: 1.590E-04 | global batch size: 512 | lm loss: 3.361857E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.055 | TFLOPs: 65.00 | +[default7]: iteration 2526/ 3814 | consumed samples: 1293312 | consumed tokens: 2648702976 | elapsed time per iteration (s): 6.04 | learning rate: 1.588E-04 | global batch size: 512 | lm loss: 3.360591E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.703 | TFLOPs: 63.98 | +[default7]: iteration 2527/ 3814 | consumed samples: 1293824 | consumed tokens: 2649751552 | elapsed time per iteration (s): 6.02 | learning rate: 1.586E-04 | global batch size: 512 | lm loss: 3.353193E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.090 | TFLOPs: 64.27 | +[default7]: iteration 2528/ 3814 | consumed samples: 1294336 | consumed tokens: 2650800128 | elapsed time per iteration (s): 6.05 | learning rate: 1.584E-04 | global batch size: 512 | lm loss: 3.359820E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.605 | TFLOPs: 63.90 | +[default7]: iteration 2529/ 3814 | consumed samples: 1294848 | consumed tokens: 2651848704 | elapsed time per iteration (s): 6.07 | learning rate: 1.582E-04 | global batch size: 512 | lm loss: 3.382142E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.314 | TFLOPs: 63.68 | +[default7]: iteration 2530/ 3814 | consumed samples: 1295360 | consumed tokens: 2652897280 | elapsed time per iteration (s): 5.98 | learning rate: 1.580E-04 | global batch size: 512 | lm loss: 3.363138E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.687 | TFLOPs: 64.72 | +[default7]: iteration 2531/ 3814 | consumed samples: 1295872 | consumed tokens: 2653945856 | elapsed time per iteration (s): 6.06 | learning rate: 1.577E-04 | global batch size: 512 | lm loss: 3.353765E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.507 | TFLOPs: 63.83 | +[default7]: iteration 2532/ 3814 | consumed samples: 1296384 | consumed tokens: 2654994432 | elapsed time per iteration (s): 5.94 | learning rate: 1.575E-04 | global batch size: 512 | lm loss: 3.363715E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.255 | TFLOPs: 65.15 | +[default7]: iteration 2533/ 3814 | consumed samples: 1296896 | consumed tokens: 2656043008 | elapsed time per iteration (s): 5.97 | learning rate: 1.573E-04 | global batch size: 512 | lm loss: 3.352304E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.738 | TFLOPs: 64.76 | +[default7]: iteration 2534/ 3814 | consumed samples: 1297408 | consumed tokens: 2657091584 | elapsed time per iteration (s): 5.98 | learning rate: 1.571E-04 | global batch size: 512 | lm loss: 3.366872E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.680 | TFLOPs: 64.71 | +[default7]: iteration 2535/ 3814 | consumed samples: 1297920 | consumed tokens: 2658140160 | elapsed time per iteration (s): 5.97 | learning rate: 1.569E-04 | global batch size: 512 | lm loss: 3.386220E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.790 | TFLOPs: 64.80 | +[default7]: iteration 2536/ 3814 | consumed samples: 1298432 | consumed tokens: 2659188736 | elapsed time per iteration (s): 6.02 | learning rate: 1.567E-04 | global batch size: 512 | lm loss: 3.357217E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.987 | TFLOPs: 64.19 | +[default7]: iteration 2537/ 3814 | consumed samples: 1298944 | consumed tokens: 2660237312 | elapsed time per iteration (s): 6.03 | learning rate: 1.564E-04 | global batch size: 512 | lm loss: 3.343392E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.961 | TFLOPs: 64.17 | +[default7]: iteration 2538/ 3814 | consumed samples: 1299456 | consumed tokens: 2661285888 | elapsed time per iteration (s): 5.99 | learning rate: 1.562E-04 | global batch size: 512 | lm loss: 3.351852E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.497 | TFLOPs: 64.58 | +[default7]: iteration 2539/ 3814 | consumed samples: 1299968 | consumed tokens: 2662334464 | elapsed time per iteration (s): 6.03 | learning rate: 1.560E-04 | global batch size: 512 | lm loss: 3.351240E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.904 | TFLOPs: 64.13 | +[default7]: iteration 2540/ 3814 | consumed samples: 1300480 | consumed tokens: 2663383040 | elapsed time per iteration (s): 6.03 | learning rate: 1.558E-04 | global batch size: 512 | lm loss: 3.368648E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.925 | TFLOPs: 64.14 | +[default7]: iteration 2541/ 3814 | consumed samples: 1300992 | consumed tokens: 2664431616 | elapsed time per iteration (s): 6.00 | learning rate: 1.556E-04 | global batch size: 512 | lm loss: 3.335946E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.303 | TFLOPs: 64.43 | +[default7]: iteration 2542/ 3814 | consumed samples: 1301504 | consumed tokens: 2665480192 | elapsed time per iteration (s): 6.00 | learning rate: 1.554E-04 | global batch size: 512 | lm loss: 3.381616E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.369 | TFLOPs: 64.48 | +[default7]: iteration 2543/ 3814 | consumed samples: 1302016 | consumed tokens: 2666528768 | elapsed time per iteration (s): 6.03 | learning rate: 1.551E-04 | global batch size: 512 | lm loss: 3.354783E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.945 | TFLOPs: 64.16 | +[default7]: iteration 2544/ 3814 | consumed samples: 1302528 | consumed tokens: 2667577344 | elapsed time per iteration (s): 6.02 | learning rate: 1.549E-04 | global batch size: 512 | lm loss: 3.337747E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.101 | TFLOPs: 64.28 | +[default7]: iteration 2545/ 3814 | consumed samples: 1303040 | consumed tokens: 2668625920 | elapsed time per iteration (s): 5.94 | learning rate: 1.547E-04 | global batch size: 512 | lm loss: 3.384214E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.169 | TFLOPs: 65.08 | +[default7]: iteration 2546/ 3814 | consumed samples: 1303552 | consumed tokens: 2669674496 | elapsed time per iteration (s): 6.02 | learning rate: 1.545E-04 | global batch size: 512 | lm loss: 3.338346E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.074 | TFLOPs: 64.26 | +[default7]: iteration 2547/ 3814 | consumed samples: 1304064 | consumed tokens: 2670723072 | elapsed time per iteration (s): 5.99 | learning rate: 1.543E-04 | global batch size: 512 | lm loss: 3.372772E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.501 | TFLOPs: 64.58 | +[default7]: iteration 2548/ 3814 | consumed samples: 1304576 | consumed tokens: 2671771648 | elapsed time per iteration (s): 5.94 | learning rate: 1.541E-04 | global batch size: 512 | lm loss: 3.365018E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.157 | TFLOPs: 65.08 | +[default7]: iteration 2549/ 3814 | consumed samples: 1305088 | consumed tokens: 2672820224 | elapsed time per iteration (s): 5.98 | learning rate: 1.538E-04 | global batch size: 512 | lm loss: 3.343493E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.599 | TFLOPs: 64.65 | +[default7]: iteration 2550/ 3814 | consumed samples: 1305600 | consumed tokens: 2673868800 | elapsed time per iteration (s): 5.98 | learning rate: 1.536E-04 | global batch size: 512 | lm loss: 3.353278E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.661 | TFLOPs: 64.70 | +[default7]: iteration 2551/ 3814 | consumed samples: 1306112 | consumed tokens: 2674917376 | elapsed time per iteration (s): 6.04 | learning rate: 1.534E-04 | global batch size: 512 | lm loss: 3.336328E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.798 | TFLOPs: 64.05 | +[default7]: iteration 2552/ 3814 | consumed samples: 1306624 | consumed tokens: 2675965952 | elapsed time per iteration (s): 6.05 | learning rate: 1.532E-04 | global batch size: 512 | lm loss: 3.348116E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.671 | TFLOPs: 63.95 | +[default7]: iteration 2553/ 3814 | consumed samples: 1307136 | consumed tokens: 2677014528 | elapsed time per iteration (s): 6.04 | learning rate: 1.530E-04 | global batch size: 512 | lm loss: 3.356773E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.789 | TFLOPs: 64.04 | +[default7]: iteration 2554/ 3814 | consumed samples: 1307648 | consumed tokens: 2678063104 | elapsed time per iteration (s): 5.97 | learning rate: 1.528E-04 | global batch size: 512 | lm loss: 3.345215E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.816 | TFLOPs: 64.82 | +[default7]: iteration 2555/ 3814 | consumed samples: 1308160 | consumed tokens: 2679111680 | elapsed time per iteration (s): 6.01 | learning rate: 1.525E-04 | global batch size: 512 | lm loss: 3.344939E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.213 | TFLOPs: 64.36 | +[default7]: iteration 2556/ 3814 | consumed samples: 1308672 | consumed tokens: 2680160256 | elapsed time per iteration (s): 6.06 | learning rate: 1.523E-04 | global batch size: 512 | lm loss: 3.370204E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.430 | TFLOPs: 63.77 | +[default7]: iteration 2557/ 3814 | consumed samples: 1309184 | consumed tokens: 2681208832 | elapsed time per iteration (s): 6.01 | learning rate: 1.521E-04 | global batch size: 512 | lm loss: 3.347266E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.180 | TFLOPs: 64.34 | +[default7]: iteration 2558/ 3814 | consumed samples: 1309696 | consumed tokens: 2682257408 | elapsed time per iteration (s): 6.05 | learning rate: 1.519E-04 | global batch size: 512 | lm loss: 3.346809E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.562 | TFLOPs: 63.87 | +[default7]: iteration 2559/ 3814 | consumed samples: 1310208 | consumed tokens: 2683305984 | elapsed time per iteration (s): 6.02 | learning rate: 1.517E-04 | global batch size: 512 | lm loss: 3.298713E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.059 | TFLOPs: 64.25 | +[default7]: iteration 2560/ 3814 | consumed samples: 1310720 | consumed tokens: 2684354560 | elapsed time per iteration (s): 5.99 | learning rate: 1.515E-04 | global batch size: 512 | lm loss: 3.355239E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.462 | TFLOPs: 64.55 | +[default7]: iteration 2561/ 3814 | consumed samples: 1311232 | consumed tokens: 2685403136 | elapsed time per iteration (s): 6.01 | learning rate: 1.513E-04 | global batch size: 512 | lm loss: 3.367949E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.141 | TFLOPs: 64.31 | +[default7]: iteration 2562/ 3814 | consumed samples: 1311744 | consumed tokens: 2686451712 | elapsed time per iteration (s): 5.95 | learning rate: 1.510E-04 | global batch size: 512 | lm loss: 3.331935E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.068 | TFLOPs: 65.01 | +[default7]: iteration 2563/ 3814 | consumed samples: 1312256 | consumed tokens: 2687500288 | elapsed time per iteration (s): 6.02 | learning rate: 1.508E-04 | global batch size: 512 | lm loss: 3.334639E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.119 | TFLOPs: 64.29 | +[default7]: iteration 2564/ 3814 | consumed samples: 1312768 | consumed tokens: 2688548864 | elapsed time per iteration (s): 6.06 | learning rate: 1.506E-04 | global batch size: 512 | lm loss: 3.350550E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.484 | TFLOPs: 63.81 | +[default7]: iteration 2565/ 3814 | consumed samples: 1313280 | consumed tokens: 2689597440 | elapsed time per iteration (s): 5.98 | learning rate: 1.504E-04 | global batch size: 512 | lm loss: 3.345528E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.605 | TFLOPs: 64.66 | +[default7]: iteration 2566/ 3814 | consumed samples: 1313792 | consumed tokens: 2690646016 | elapsed time per iteration (s): 6.02 | learning rate: 1.502E-04 | global batch size: 512 | lm loss: 3.365133E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.003 | TFLOPs: 64.20 | +[default7]: iteration 2567/ 3814 | consumed samples: 1314304 | consumed tokens: 2691694592 | elapsed time per iteration (s): 6.05 | learning rate: 1.500E-04 | global batch size: 512 | lm loss: 3.362423E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.646 | TFLOPs: 63.93 | +[default7]: iteration 2568/ 3814 | consumed samples: 1314816 | consumed tokens: 2692743168 | elapsed time per iteration (s): 5.96 | learning rate: 1.498E-04 | global batch size: 512 | lm loss: 3.343204E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.881 | TFLOPs: 64.87 | +[default7]: iteration 2569/ 3814 | consumed samples: 1315328 | consumed tokens: 2693791744 | elapsed time per iteration (s): 6.02 | learning rate: 1.495E-04 | global batch size: 512 | lm loss: 3.357199E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.992 | TFLOPs: 64.20 | +[default7]: iteration 2570/ 3814 | consumed samples: 1315840 | consumed tokens: 2694840320 | elapsed time per iteration (s): 6.01 | learning rate: 1.493E-04 | global batch size: 512 | lm loss: 3.365957E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.223 | TFLOPs: 64.37 | +[default7]: iteration 2571/ 3814 | consumed samples: 1316352 | consumed tokens: 2695888896 | elapsed time per iteration (s): 6.09 | learning rate: 1.491E-04 | global batch size: 512 | lm loss: 3.351799E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.138 | TFLOPs: 63.55 | +[default7]: iteration 2572/ 3814 | consumed samples: 1316864 | consumed tokens: 2696937472 | elapsed time per iteration (s): 5.74 | learning rate: 1.489E-04 | global batch size: 512 | lm loss: 3.360557E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.247 | TFLOPs: 67.41 | +[default7]: iteration 2573/ 3814 | consumed samples: 1317376 | consumed tokens: 2697986048 | elapsed time per iteration (s): 6.05 | learning rate: 1.487E-04 | global batch size: 512 | lm loss: 3.363533E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.565 | TFLOPs: 63.87 | +[default7]: iteration 2574/ 3814 | consumed samples: 1317888 | consumed tokens: 2699034624 | elapsed time per iteration (s): 6.20 | learning rate: 1.485E-04 | global batch size: 512 | lm loss: 3.371871E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.541 | TFLOPs: 62.34 | +[default7]: iteration 2575/ 3814 | consumed samples: 1318400 | consumed tokens: 2700083200 | elapsed time per iteration (s): 6.04 | learning rate: 1.483E-04 | global batch size: 512 | lm loss: 3.328133E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.831 | TFLOPs: 64.07 | +[default7]: iteration 2576/ 3814 | consumed samples: 1318912 | consumed tokens: 2701131776 | elapsed time per iteration (s): 6.04 | learning rate: 1.480E-04 | global batch size: 512 | lm loss: 3.352784E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.825 | TFLOPs: 64.07 | +[default7]: iteration 2577/ 3814 | consumed samples: 1319424 | consumed tokens: 2702180352 | elapsed time per iteration (s): 6.06 | learning rate: 1.478E-04 | global batch size: 512 | lm loss: 3.362620E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.501 | TFLOPs: 63.82 | +[default7]: iteration 2578/ 3814 | consumed samples: 1319936 | consumed tokens: 2703228928 | elapsed time per iteration (s): 5.94 | learning rate: 1.476E-04 | global batch size: 512 | lm loss: 3.392682E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.259 | TFLOPs: 65.15 | +[default7]: iteration 2579/ 3814 | consumed samples: 1320448 | consumed tokens: 2704277504 | elapsed time per iteration (s): 6.06 | learning rate: 1.474E-04 | global batch size: 512 | lm loss: 3.371978E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.513 | TFLOPs: 63.83 | +[default7]: iteration 2580/ 3814 | consumed samples: 1320960 | consumed tokens: 2705326080 | elapsed time per iteration (s): 5.98 | learning rate: 1.472E-04 | global batch size: 512 | lm loss: 3.336004E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.568 | TFLOPs: 64.63 | +[default7]: iteration 2581/ 3814 | consumed samples: 1321472 | consumed tokens: 2706374656 | elapsed time per iteration (s): 6.00 | learning rate: 1.470E-04 | global batch size: 512 | lm loss: 3.320363E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.305 | TFLOPs: 64.43 | +[default7]: iteration 2582/ 3814 | consumed samples: 1321984 | consumed tokens: 2707423232 | elapsed time per iteration (s): 6.06 | learning rate: 1.468E-04 | global batch size: 512 | lm loss: 3.368706E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.458 | TFLOPs: 63.79 | +[default7]: iteration 2583/ 3814 | consumed samples: 1322496 | consumed tokens: 2708471808 | elapsed time per iteration (s): 6.22 | learning rate: 1.466E-04 | global batch size: 512 | lm loss: 3.340514E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.266 | TFLOPs: 62.14 | +[default7]: iteration 2584/ 3814 | consumed samples: 1323008 | consumed tokens: 2709520384 | elapsed time per iteration (s): 6.03 | learning rate: 1.463E-04 | global batch size: 512 | lm loss: 3.337913E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.909 | TFLOPs: 64.13 | +[default7]: iteration 2585/ 3814 | consumed samples: 1323520 | consumed tokens: 2710568960 | elapsed time per iteration (s): 6.10 | learning rate: 1.461E-04 | global batch size: 512 | lm loss: 3.337968E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.941 | TFLOPs: 63.40 | +[default7]: iteration 2586/ 3814 | consumed samples: 1324032 | consumed tokens: 2711617536 | elapsed time per iteration (s): 6.14 | learning rate: 1.459E-04 | global batch size: 512 | lm loss: 3.337795E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.395 | TFLOPs: 62.99 | +[default7]: iteration 2587/ 3814 | consumed samples: 1324544 | consumed tokens: 2712666112 | elapsed time per iteration (s): 6.15 | learning rate: 1.457E-04 | global batch size: 512 | lm loss: 3.339495E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.238 | TFLOPs: 62.87 | +[default7]: iteration 2588/ 3814 | consumed samples: 1325056 | consumed tokens: 2713714688 | elapsed time per iteration (s): 6.18 | learning rate: 1.455E-04 | global batch size: 512 | lm loss: 3.339630E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.835 | TFLOPs: 62.57 | +[default7]: iteration 2589/ 3814 | consumed samples: 1325568 | consumed tokens: 2714763264 | elapsed time per iteration (s): 6.15 | learning rate: 1.453E-04 | global batch size: 512 | lm loss: 3.328104E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.186 | TFLOPs: 62.83 | +[default7]: iteration 2590/ 3814 | consumed samples: 1326080 | consumed tokens: 2715811840 | elapsed time per iteration (s): 5.98 | learning rate: 1.451E-04 | global batch size: 512 | lm loss: 3.345997E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.639 | TFLOPs: 64.68 | +[default7]: iteration 2591/ 3814 | consumed samples: 1326592 | consumed tokens: 2716860416 | elapsed time per iteration (s): 6.05 | learning rate: 1.449E-04 | global batch size: 512 | lm loss: 3.345639E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.613 | TFLOPs: 63.91 | +[default7]: iteration 2592/ 3814 | consumed samples: 1327104 | consumed tokens: 2717908992 | elapsed time per iteration (s): 6.06 | learning rate: 1.446E-04 | global batch size: 512 | lm loss: 3.363218E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.459 | TFLOPs: 63.79 | +[default7]: iteration 2593/ 3814 | consumed samples: 1327616 | consumed tokens: 2718957568 | elapsed time per iteration (s): 6.07 | learning rate: 1.444E-04 | global batch size: 512 | lm loss: 3.336366E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.321 | TFLOPs: 63.69 | +[default7]: iteration 2594/ 3814 | consumed samples: 1328128 | consumed tokens: 2720006144 | elapsed time per iteration (s): 6.05 | learning rate: 1.442E-04 | global batch size: 512 | lm loss: 3.362251E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.569 | TFLOPs: 63.88 | +[default7]: iteration 2595/ 3814 | consumed samples: 1328640 | consumed tokens: 2721054720 | elapsed time per iteration (s): 6.06 | learning rate: 1.440E-04 | global batch size: 512 | lm loss: 3.355348E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.499 | TFLOPs: 63.82 | +[default7]: iteration 2596/ 3814 | consumed samples: 1329152 | consumed tokens: 2722103296 | elapsed time per iteration (s): 6.02 | learning rate: 1.438E-04 | global batch size: 512 | lm loss: 3.330532E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.104 | TFLOPs: 64.28 | +[default7]: iteration 2597/ 3814 | consumed samples: 1329664 | consumed tokens: 2723151872 | elapsed time per iteration (s): 6.04 | learning rate: 1.436E-04 | global batch size: 512 | lm loss: 3.362548E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.819 | TFLOPs: 64.06 | +[default7]: iteration 2598/ 3814 | consumed samples: 1330176 | consumed tokens: 2724200448 | elapsed time per iteration (s): 5.96 | learning rate: 1.434E-04 | global batch size: 512 | lm loss: 3.348048E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.900 | TFLOPs: 64.88 | +[default7]: iteration 2599/ 3814 | consumed samples: 1330688 | consumed tokens: 2725249024 | elapsed time per iteration (s): 6.04 | learning rate: 1.432E-04 | global batch size: 512 | lm loss: 3.352718E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.740 | TFLOPs: 64.00 | +[default7]: iteration 2600/ 3814 | consumed samples: 1331200 | consumed tokens: 2726297600 | elapsed time per iteration (s): 5.94 | learning rate: 1.430E-04 | global batch size: 512 | lm loss: 3.315303E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.148 | TFLOPs: 65.07 | +[default7]: iteration 2601/ 3814 | consumed samples: 1331712 | consumed tokens: 2727346176 | elapsed time per iteration (s): 6.05 | learning rate: 1.427E-04 | global batch size: 512 | lm loss: 3.348234E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.633 | TFLOPs: 63.92 | +[default7]: iteration 2602/ 3814 | consumed samples: 1332224 | consumed tokens: 2728394752 | elapsed time per iteration (s): 6.02 | learning rate: 1.425E-04 | global batch size: 512 | lm loss: 3.336815E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.089 | TFLOPs: 64.27 | +[default7]: iteration 2603/ 3814 | consumed samples: 1332736 | consumed tokens: 2729443328 | elapsed time per iteration (s): 5.89 | learning rate: 1.423E-04 | global batch size: 512 | lm loss: 3.355686E+00 | loss scale: 131072.0 | grad norm: 0.140 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.906 | TFLOPs: 65.64 | +[default7]: iteration 2604/ 3814 | consumed samples: 1333248 | consumed tokens: 2730491904 | elapsed time per iteration (s): 6.02 | learning rate: 1.421E-04 | global batch size: 512 | lm loss: 3.335519E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.057 | TFLOPs: 64.24 | +[default7]: iteration 2605/ 3814 | consumed samples: 1333760 | consumed tokens: 2731540480 | elapsed time per iteration (s): 6.01 | learning rate: 1.419E-04 | global batch size: 512 | lm loss: 3.316795E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.152 | TFLOPs: 64.32 | +[default7]: iteration 2606/ 3814 | consumed samples: 1334272 | consumed tokens: 2732589056 | elapsed time per iteration (s): 6.02 | learning rate: 1.417E-04 | global batch size: 512 | lm loss: 3.334428E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.987 | TFLOPs: 64.19 | +[default7]: iteration 2607/ 3814 | consumed samples: 1334784 | consumed tokens: 2733637632 | elapsed time per iteration (s): 5.95 | learning rate: 1.415E-04 | global batch size: 512 | lm loss: 3.372622E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.034 | TFLOPs: 64.98 | +[default7]: iteration 2608/ 3814 | consumed samples: 1335296 | consumed tokens: 2734686208 | elapsed time per iteration (s): 6.00 | learning rate: 1.413E-04 | global batch size: 512 | lm loss: 3.305801E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.361 | TFLOPs: 64.47 | +[default7]: iteration 2609/ 3814 | consumed samples: 1335808 | consumed tokens: 2735734784 | elapsed time per iteration (s): 6.02 | learning rate: 1.411E-04 | global batch size: 512 | lm loss: 3.362471E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.099 | TFLOPs: 64.28 | +[default7]: iteration 2610/ 3814 | consumed samples: 1336320 | consumed tokens: 2736783360 | elapsed time per iteration (s): 6.04 | learning rate: 1.409E-04 | global batch size: 512 | lm loss: 3.337605E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.746 | TFLOPs: 64.01 | +[default7]: iteration 2611/ 3814 | consumed samples: 1336832 | consumed tokens: 2737831936 | elapsed time per iteration (s): 5.96 | learning rate: 1.406E-04 | global batch size: 512 | lm loss: 3.350092E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.872 | TFLOPs: 64.86 | +[default7]: iteration 2612/ 3814 | consumed samples: 1337344 | consumed tokens: 2738880512 | elapsed time per iteration (s): 6.22 | learning rate: 1.404E-04 | global batch size: 512 | lm loss: 3.358233E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.291 | TFLOPs: 62.16 | +[default7]: iteration 2613/ 3814 | consumed samples: 1337856 | consumed tokens: 2739929088 | elapsed time per iteration (s): 6.19 | learning rate: 1.402E-04 | global batch size: 512 | lm loss: 3.324239E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.774 | TFLOPs: 62.52 | +[default7]: iteration 2614/ 3814 | consumed samples: 1338368 | consumed tokens: 2740977664 | elapsed time per iteration (s): 5.85 | learning rate: 1.400E-04 | global batch size: 512 | lm loss: 3.336770E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.489 | TFLOPs: 66.08 | +[default7]: iteration 2615/ 3814 | consumed samples: 1338880 | consumed tokens: 2742026240 | elapsed time per iteration (s): 6.05 | learning rate: 1.398E-04 | global batch size: 512 | lm loss: 3.367854E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.628 | TFLOPs: 63.92 | +[default7]: iteration 2616/ 3814 | consumed samples: 1339392 | consumed tokens: 2743074816 | elapsed time per iteration (s): 6.05 | learning rate: 1.396E-04 | global batch size: 512 | lm loss: 3.341392E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.698 | TFLOPs: 63.97 | +[default7]: iteration 2617/ 3814 | consumed samples: 1339904 | consumed tokens: 2744123392 | elapsed time per iteration (s): 6.04 | learning rate: 1.394E-04 | global batch size: 512 | lm loss: 3.359918E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.806 | TFLOPs: 64.05 | +[default7]: iteration 2618/ 3814 | consumed samples: 1340416 | consumed tokens: 2745171968 | elapsed time per iteration (s): 6.02 | learning rate: 1.392E-04 | global batch size: 512 | lm loss: 3.352036E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.025 | TFLOPs: 64.22 | +[default7]: iteration 2619/ 3814 | consumed samples: 1340928 | consumed tokens: 2746220544 | elapsed time per iteration (s): 6.18 | learning rate: 1.390E-04 | global batch size: 512 | lm loss: 3.331766E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.908 | TFLOPs: 62.62 | +[default7]: iteration 2620/ 3814 | consumed samples: 1341440 | consumed tokens: 2747269120 | elapsed time per iteration (s): 5.95 | learning rate: 1.388E-04 | global batch size: 512 | lm loss: 3.317893E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.045 | TFLOPs: 64.99 | +[default7]: iteration 2621/ 3814 | consumed samples: 1341952 | consumed tokens: 2748317696 | elapsed time per iteration (s): 6.20 | learning rate: 1.385E-04 | global batch size: 512 | lm loss: 3.343024E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.627 | TFLOPs: 62.41 | +[default7]: iteration 2622/ 3814 | consumed samples: 1342464 | consumed tokens: 2749366272 | elapsed time per iteration (s): 5.99 | learning rate: 1.383E-04 | global batch size: 512 | lm loss: 3.310236E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.463 | TFLOPs: 64.55 | +[default7]: iteration 2623/ 3814 | consumed samples: 1342976 | consumed tokens: 2750414848 | elapsed time per iteration (s): 5.96 | learning rate: 1.381E-04 | global batch size: 512 | lm loss: 3.349034E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.952 | TFLOPs: 64.92 | +[default7]: iteration 2624/ 3814 | consumed samples: 1343488 | consumed tokens: 2751463424 | elapsed time per iteration (s): 6.11 | learning rate: 1.379E-04 | global batch size: 512 | lm loss: 3.352783E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.822 | TFLOPs: 63.31 | +[default7]: iteration 2625/ 3814 | consumed samples: 1344000 | consumed tokens: 2752512000 | elapsed time per iteration (s): 6.14 | learning rate: 1.377E-04 | global batch size: 512 | lm loss: 3.334523E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.424 | TFLOPs: 63.01 | +[default7]: iteration 2626/ 3814 | consumed samples: 1344512 | consumed tokens: 2753560576 | elapsed time per iteration (s): 5.96 | learning rate: 1.375E-04 | global batch size: 512 | lm loss: 3.346418E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.894 | TFLOPs: 64.88 | +[default7]: iteration 2627/ 3814 | consumed samples: 1345024 | consumed tokens: 2754609152 | elapsed time per iteration (s): 6.12 | learning rate: 1.373E-04 | global batch size: 512 | lm loss: 3.329077E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.632 | TFLOPs: 63.17 | +[default7]: iteration 2628/ 3814 | consumed samples: 1345536 | consumed tokens: 2755657728 | elapsed time per iteration (s): 6.14 | learning rate: 1.371E-04 | global batch size: 512 | lm loss: 3.352719E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.327 | TFLOPs: 62.94 | +[default7]: iteration 2629/ 3814 | consumed samples: 1346048 | consumed tokens: 2756706304 | elapsed time per iteration (s): 6.24 | learning rate: 1.369E-04 | global batch size: 512 | lm loss: 3.324765E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.031 | TFLOPs: 61.96 | +[default7]: iteration 2630/ 3814 | consumed samples: 1346560 | consumed tokens: 2757754880 | elapsed time per iteration (s): 6.14 | learning rate: 1.367E-04 | global batch size: 512 | lm loss: 3.350874E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.381 | TFLOPs: 62.98 | +[default7]: iteration 2631/ 3814 | consumed samples: 1347072 | consumed tokens: 2758803456 | elapsed time per iteration (s): 6.04 | learning rate: 1.365E-04 | global batch size: 512 | lm loss: 3.347183E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.704 | TFLOPs: 63.98 | +[default7]: iteration 2632/ 3814 | consumed samples: 1347584 | consumed tokens: 2759852032 | elapsed time per iteration (s): 5.98 | learning rate: 1.363E-04 | global batch size: 512 | lm loss: 3.367843E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.647 | TFLOPs: 64.69 | +[default7]: iteration 2633/ 3814 | consumed samples: 1348096 | consumed tokens: 2760900608 | elapsed time per iteration (s): 6.13 | learning rate: 1.360E-04 | global batch size: 512 | lm loss: 3.336191E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.493 | TFLOPs: 63.06 | +[default7]: iteration 2634/ 3814 | consumed samples: 1348608 | consumed tokens: 2761949184 | elapsed time per iteration (s): 6.06 | learning rate: 1.358E-04 | global batch size: 512 | lm loss: 3.323158E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.549 | TFLOPs: 63.86 | +[default7]: iteration 2635/ 3814 | consumed samples: 1349120 | consumed tokens: 2762997760 | elapsed time per iteration (s): 6.09 | learning rate: 1.356E-04 | global batch size: 512 | lm loss: 3.359013E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.056 | TFLOPs: 63.49 | +[default7]: iteration 2636/ 3814 | consumed samples: 1349632 | consumed tokens: 2764046336 | elapsed time per iteration (s): 6.17 | learning rate: 1.354E-04 | global batch size: 512 | lm loss: 3.311924E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.031 | TFLOPs: 62.71 | +[default7]: iteration 2637/ 3814 | consumed samples: 1350144 | consumed tokens: 2765094912 | elapsed time per iteration (s): 6.04 | learning rate: 1.352E-04 | global batch size: 512 | lm loss: 3.341369E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.820 | TFLOPs: 64.07 | +[default7]: iteration 2638/ 3814 | consumed samples: 1350656 | consumed tokens: 2766143488 | elapsed time per iteration (s): 5.91 | learning rate: 1.350E-04 | global batch size: 512 | lm loss: 3.333551E+00 | loss scale: 131072.0 | grad norm: 0.147 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.635 | TFLOPs: 65.44 | +[default7]: iteration 2639/ 3814 | consumed samples: 1351168 | consumed tokens: 2767192064 | elapsed time per iteration (s): 6.01 | learning rate: 1.348E-04 | global batch size: 512 | lm loss: 3.337483E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.228 | TFLOPs: 64.37 | +[default7]: iteration 2640/ 3814 | consumed samples: 1351680 | consumed tokens: 2768240640 | elapsed time per iteration (s): 5.99 | learning rate: 1.346E-04 | global batch size: 512 | lm loss: 3.340339E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.413 | TFLOPs: 64.51 | +[default7]: iteration 2641/ 3814 | consumed samples: 1352192 | consumed tokens: 2769289216 | elapsed time per iteration (s): 6.10 | learning rate: 1.344E-04 | global batch size: 512 | lm loss: 3.313801E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.964 | TFLOPs: 63.42 | +[default7]: iteration 2642/ 3814 | consumed samples: 1352704 | consumed tokens: 2770337792 | elapsed time per iteration (s): 6.05 | learning rate: 1.342E-04 | global batch size: 512 | lm loss: 3.344120E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.572 | TFLOPs: 63.88 | +[default7]: iteration 2643/ 3814 | consumed samples: 1353216 | consumed tokens: 2771386368 | elapsed time per iteration (s): 5.91 | learning rate: 1.340E-04 | global batch size: 512 | lm loss: 3.339134E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.702 | TFLOPs: 65.49 | +[default7]: iteration 2644/ 3814 | consumed samples: 1353728 | consumed tokens: 2772434944 | elapsed time per iteration (s): 6.04 | learning rate: 1.338E-04 | global batch size: 512 | lm loss: 3.311576E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.818 | TFLOPs: 64.06 | +[default7]: iteration 2645/ 3814 | consumed samples: 1354240 | consumed tokens: 2773483520 | elapsed time per iteration (s): 6.16 | learning rate: 1.336E-04 | global batch size: 512 | lm loss: 3.329097E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.072 | TFLOPs: 62.75 | +[default7]: iteration 2646/ 3814 | consumed samples: 1354752 | consumed tokens: 2774532096 | elapsed time per iteration (s): 5.75 | learning rate: 1.334E-04 | global batch size: 512 | lm loss: 3.316997E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 89.114 | TFLOPs: 67.31 | +[default7]: iteration 2647/ 3814 | consumed samples: 1355264 | consumed tokens: 2775580672 | elapsed time per iteration (s): 6.07 | learning rate: 1.332E-04 | global batch size: 512 | lm loss: 3.341830E+00 | loss scale: 131072.0 | grad norm: 0.139 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.331 | TFLOPs: 63.70 | +[default7]: iteration 2648/ 3814 | consumed samples: 1355776 | consumed tokens: 2776629248 | elapsed time per iteration (s): 6.16 | learning rate: 1.329E-04 | global batch size: 512 | lm loss: 3.317580E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.081 | TFLOPs: 62.75 | +[default7]: iteration 2649/ 3814 | consumed samples: 1356288 | consumed tokens: 2777677824 | elapsed time per iteration (s): 6.13 | learning rate: 1.327E-04 | global batch size: 512 | lm loss: 3.331779E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.552 | TFLOPs: 63.11 | +[default7]: iteration 2650/ 3814 | consumed samples: 1356800 | consumed tokens: 2778726400 | elapsed time per iteration (s): 6.16 | learning rate: 1.325E-04 | global batch size: 512 | lm loss: 3.325538E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.093 | TFLOPs: 62.76 | +[default7]: iteration 2651/ 3814 | consumed samples: 1357312 | consumed tokens: 2779774976 | elapsed time per iteration (s): 6.17 | learning rate: 1.323E-04 | global batch size: 512 | lm loss: 3.305010E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.020 | TFLOPs: 62.71 | +[default7]: iteration 2652/ 3814 | consumed samples: 1357824 | consumed tokens: 2780823552 | elapsed time per iteration (s): 6.16 | learning rate: 1.321E-04 | global batch size: 512 | lm loss: 3.325918E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.109 | TFLOPs: 62.77 | +[default7]: iteration 2653/ 3814 | consumed samples: 1358336 | consumed tokens: 2781872128 | elapsed time per iteration (s): 6.13 | learning rate: 1.319E-04 | global batch size: 512 | lm loss: 3.347854E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.470 | TFLOPs: 63.05 | +[default7]: iteration 2654/ 3814 | consumed samples: 1358848 | consumed tokens: 2782920704 | elapsed time per iteration (s): 6.16 | learning rate: 1.317E-04 | global batch size: 512 | lm loss: 3.349362E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.069 | TFLOPs: 62.74 | +[default7]: iteration 2655/ 3814 | consumed samples: 1359360 | consumed tokens: 2783969280 | elapsed time per iteration (s): 6.14 | learning rate: 1.315E-04 | global batch size: 512 | lm loss: 3.344016E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.426 | TFLOPs: 63.01 | +[default7]: iteration 2656/ 3814 | consumed samples: 1359872 | consumed tokens: 2785017856 | elapsed time per iteration (s): 6.22 | learning rate: 1.313E-04 | global batch size: 512 | lm loss: 3.342788E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.285 | TFLOPs: 62.15 | +[default7]: iteration 2657/ 3814 | consumed samples: 1360384 | consumed tokens: 2786066432 | elapsed time per iteration (s): 6.22 | learning rate: 1.311E-04 | global batch size: 512 | lm loss: 3.350938E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.322 | TFLOPs: 62.18 | +[default7]: iteration 2658/ 3814 | consumed samples: 1360896 | consumed tokens: 2787115008 | elapsed time per iteration (s): 6.19 | learning rate: 1.309E-04 | global batch size: 512 | lm loss: 3.344253E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.677 | TFLOPs: 62.45 | +[default7]: iteration 2659/ 3814 | consumed samples: 1361408 | consumed tokens: 2788163584 | elapsed time per iteration (s): 6.16 | learning rate: 1.307E-04 | global batch size: 512 | lm loss: 3.344417E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.088 | TFLOPs: 62.76 | +[default7]: iteration 2660/ 3814 | consumed samples: 1361920 | consumed tokens: 2789212160 | elapsed time per iteration (s): 6.12 | learning rate: 1.305E-04 | global batch size: 512 | lm loss: 3.338635E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.599 | TFLOPs: 63.14 | +[default7]: iteration 2661/ 3814 | consumed samples: 1362432 | consumed tokens: 2790260736 | elapsed time per iteration (s): 6.02 | learning rate: 1.303E-04 | global batch size: 512 | lm loss: 3.354512E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.068 | TFLOPs: 64.25 | +[default7]: iteration 2662/ 3814 | consumed samples: 1362944 | consumed tokens: 2791309312 | elapsed time per iteration (s): 6.18 | learning rate: 1.301E-04 | global batch size: 512 | lm loss: 3.333176E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.858 | TFLOPs: 62.58 | +[default7]: iteration 2663/ 3814 | consumed samples: 1363456 | consumed tokens: 2792357888 | elapsed time per iteration (s): 6.18 | learning rate: 1.299E-04 | global batch size: 512 | lm loss: 3.309221E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.835 | TFLOPs: 62.57 | +[default7]: iteration 2664/ 3814 | consumed samples: 1363968 | consumed tokens: 2793406464 | elapsed time per iteration (s): 6.16 | learning rate: 1.297E-04 | global batch size: 512 | lm loss: 3.296940E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.160 | TFLOPs: 62.81 | +[default7]: iteration 2665/ 3814 | consumed samples: 1364480 | consumed tokens: 2794455040 | elapsed time per iteration (s): 6.25 | learning rate: 1.295E-04 | global batch size: 512 | lm loss: 3.309468E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 81.949 | TFLOPs: 61.90 | +[default7]: iteration 2666/ 3814 | consumed samples: 1364992 | consumed tokens: 2795503616 | elapsed time per iteration (s): 6.09 | learning rate: 1.293E-04 | global batch size: 512 | lm loss: 3.324513E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.101 | TFLOPs: 63.52 | +[default7]: iteration 2667/ 3814 | consumed samples: 1365504 | consumed tokens: 2796552192 | elapsed time per iteration (s): 6.14 | learning rate: 1.290E-04 | global batch size: 512 | lm loss: 3.325998E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.354 | TFLOPs: 62.96 | +[default7]: iteration 2668/ 3814 | consumed samples: 1366016 | consumed tokens: 2797600768 | elapsed time per iteration (s): 6.14 | learning rate: 1.288E-04 | global batch size: 512 | lm loss: 3.352137E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.384 | TFLOPs: 62.98 | +[default7]: iteration 2669/ 3814 | consumed samples: 1366528 | consumed tokens: 2798649344 | elapsed time per iteration (s): 6.13 | learning rate: 1.286E-04 | global batch size: 512 | lm loss: 3.336510E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.538 | TFLOPs: 63.10 | +[default7]: iteration 2670/ 3814 | consumed samples: 1367040 | consumed tokens: 2799697920 | elapsed time per iteration (s): 6.14 | learning rate: 1.284E-04 | global batch size: 512 | lm loss: 3.319410E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.331 | TFLOPs: 62.94 | +[default7]: iteration 2671/ 3814 | consumed samples: 1367552 | consumed tokens: 2800746496 | elapsed time per iteration (s): 6.04 | learning rate: 1.282E-04 | global batch size: 512 | lm loss: 3.330665E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.720 | TFLOPs: 63.99 | +[default7]: iteration 2672/ 3814 | consumed samples: 1368064 | consumed tokens: 2801795072 | elapsed time per iteration (s): 6.17 | learning rate: 1.280E-04 | global batch size: 512 | lm loss: 3.330342E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.965 | TFLOPs: 62.66 | +[default7]: iteration 2673/ 3814 | consumed samples: 1368576 | consumed tokens: 2802843648 | elapsed time per iteration (s): 6.17 | learning rate: 1.278E-04 | global batch size: 512 | lm loss: 3.341223E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.995 | TFLOPs: 62.69 | +[default7]: iteration 2674/ 3814 | consumed samples: 1369088 | consumed tokens: 2803892224 | elapsed time per iteration (s): 6.09 | learning rate: 1.276E-04 | global batch size: 512 | lm loss: 3.320724E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.041 | TFLOPs: 63.48 | +[default7]: iteration 2675/ 3814 | consumed samples: 1369600 | consumed tokens: 2804940800 | elapsed time per iteration (s): 5.99 | learning rate: 1.274E-04 | global batch size: 512 | lm loss: 3.306695E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.424 | TFLOPs: 64.52 | +[default7]: iteration 2676/ 3814 | consumed samples: 1370112 | consumed tokens: 2805989376 | elapsed time per iteration (s): 5.97 | learning rate: 1.272E-04 | global batch size: 512 | lm loss: 3.328032E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.825 | TFLOPs: 64.82 | +[default7]: iteration 2677/ 3814 | consumed samples: 1370624 | consumed tokens: 2807037952 | elapsed time per iteration (s): 6.13 | learning rate: 1.270E-04 | global batch size: 512 | lm loss: 3.359980E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.482 | TFLOPs: 63.05 | +[default7]: iteration 2678/ 3814 | consumed samples: 1371136 | consumed tokens: 2808086528 | elapsed time per iteration (s): 6.12 | learning rate: 1.268E-04 | global batch size: 512 | lm loss: 3.373652E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.660 | TFLOPs: 63.19 | +[default7]: iteration 2679/ 3814 | consumed samples: 1371648 | consumed tokens: 2809135104 | elapsed time per iteration (s): 6.14 | learning rate: 1.266E-04 | global batch size: 512 | lm loss: 3.328402E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.424 | TFLOPs: 63.01 | +[default7]: iteration 2680/ 3814 | consumed samples: 1372160 | consumed tokens: 2810183680 | elapsed time per iteration (s): 6.14 | learning rate: 1.264E-04 | global batch size: 512 | lm loss: 3.339488E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.370 | TFLOPs: 62.97 | +[default7]: iteration 2681/ 3814 | consumed samples: 1372672 | consumed tokens: 2811232256 | elapsed time per iteration (s): 6.17 | learning rate: 1.262E-04 | global batch size: 512 | lm loss: 3.288764E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.011 | TFLOPs: 62.70 | +[default7]: iteration 2682/ 3814 | consumed samples: 1373184 | consumed tokens: 2812280832 | elapsed time per iteration (s): 6.11 | learning rate: 1.260E-04 | global batch size: 512 | lm loss: 3.337319E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.787 | TFLOPs: 63.28 | +[default7]: iteration 2683/ 3814 | consumed samples: 1373696 | consumed tokens: 2813329408 | elapsed time per iteration (s): 6.12 | learning rate: 1.258E-04 | global batch size: 512 | lm loss: 3.310766E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.626 | TFLOPs: 63.16 | +[default7]: iteration 2684/ 3814 | consumed samples: 1374208 | consumed tokens: 2814377984 | elapsed time per iteration (s): 6.02 | learning rate: 1.256E-04 | global batch size: 512 | lm loss: 3.298050E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.000 | TFLOPs: 64.20 | +[default7]: iteration 2685/ 3814 | consumed samples: 1374720 | consumed tokens: 2815426560 | elapsed time per iteration (s): 5.98 | learning rate: 1.254E-04 | global batch size: 512 | lm loss: 3.319157E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.636 | TFLOPs: 64.68 | +[default7]: iteration 2686/ 3814 | consumed samples: 1375232 | consumed tokens: 2816475136 | elapsed time per iteration (s): 5.96 | learning rate: 1.252E-04 | global batch size: 512 | lm loss: 3.329818E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.871 | TFLOPs: 64.86 | +[default7]: iteration 2687/ 3814 | consumed samples: 1375744 | consumed tokens: 2817523712 | elapsed time per iteration (s): 6.04 | learning rate: 1.250E-04 | global batch size: 512 | lm loss: 3.315756E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.815 | TFLOPs: 64.06 | +[default7]: iteration 2688/ 3814 | consumed samples: 1376256 | consumed tokens: 2818572288 | elapsed time per iteration (s): 5.82 | learning rate: 1.248E-04 | global batch size: 512 | lm loss: 3.341091E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.037 | TFLOPs: 66.49 | +[default7]: iteration 2689/ 3814 | consumed samples: 1376768 | consumed tokens: 2819620864 | elapsed time per iteration (s): 6.15 | learning rate: 1.246E-04 | global batch size: 512 | lm loss: 3.334975E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.205 | TFLOPs: 62.85 | +[default7]: iteration 2690/ 3814 | consumed samples: 1377280 | consumed tokens: 2820669440 | elapsed time per iteration (s): 6.15 | learning rate: 1.244E-04 | global batch size: 512 | lm loss: 3.308822E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.233 | TFLOPs: 62.87 | +[default7]: iteration 2691/ 3814 | consumed samples: 1377792 | consumed tokens: 2821718016 | elapsed time per iteration (s): 6.11 | learning rate: 1.242E-04 | global batch size: 512 | lm loss: 3.311721E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.791 | TFLOPs: 63.29 | +[default7]: iteration 2692/ 3814 | consumed samples: 1378304 | consumed tokens: 2822766592 | elapsed time per iteration (s): 6.16 | learning rate: 1.240E-04 | global batch size: 512 | lm loss: 3.323183E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.114 | TFLOPs: 62.78 | +[default7]: iteration 2693/ 3814 | consumed samples: 1378816 | consumed tokens: 2823815168 | elapsed time per iteration (s): 6.04 | learning rate: 1.238E-04 | global batch size: 512 | lm loss: 3.324477E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.788 | TFLOPs: 64.04 | +[default7]: iteration 2694/ 3814 | consumed samples: 1379328 | consumed tokens: 2824863744 | elapsed time per iteration (s): 5.90 | learning rate: 1.236E-04 | global batch size: 512 | lm loss: 3.329805E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.749 | TFLOPs: 65.52 | +[default7]: iteration 2695/ 3814 | consumed samples: 1379840 | consumed tokens: 2825912320 | elapsed time per iteration (s): 6.05 | learning rate: 1.234E-04 | global batch size: 512 | lm loss: 3.340318E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.596 | TFLOPs: 63.90 | +[default7]: iteration 2696/ 3814 | consumed samples: 1380352 | consumed tokens: 2826960896 | elapsed time per iteration (s): 5.96 | learning rate: 1.232E-04 | global batch size: 512 | lm loss: 3.354293E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.922 | TFLOPs: 64.90 | +[default7]: iteration 2697/ 3814 | consumed samples: 1380864 | consumed tokens: 2828009472 | elapsed time per iteration (s): 5.96 | learning rate: 1.230E-04 | global batch size: 512 | lm loss: 3.313328E+00 | loss scale: 131072.0 | grad norm: 0.136 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.856 | TFLOPs: 64.85 | +[default7]: iteration 2698/ 3814 | consumed samples: 1381376 | consumed tokens: 2829058048 | elapsed time per iteration (s): 6.01 | learning rate: 1.228E-04 | global batch size: 512 | lm loss: 3.383707E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.197 | TFLOPs: 64.35 | +[default7]: iteration 2699/ 3814 | consumed samples: 1381888 | consumed tokens: 2830106624 | elapsed time per iteration (s): 6.02 | learning rate: 1.226E-04 | global batch size: 512 | lm loss: 3.343836E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.073 | TFLOPs: 64.26 | +[default7]: iteration 2700/ 3814 | consumed samples: 1382400 | consumed tokens: 2831155200 | elapsed time per iteration (s): 6.05 | learning rate: 1.224E-04 | global batch size: 512 | lm loss: 3.329833E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.680 | TFLOPs: 63.96 | +[default7]: iteration 2701/ 3814 | consumed samples: 1382912 | consumed tokens: 2832203776 | elapsed time per iteration (s): 5.96 | learning rate: 1.222E-04 | global batch size: 512 | lm loss: 3.324970E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.895 | TFLOPs: 64.88 | +[default7]: iteration 2702/ 3814 | consumed samples: 1383424 | consumed tokens: 2833252352 | elapsed time per iteration (s): 6.02 | learning rate: 1.220E-04 | global batch size: 512 | lm loss: 3.340311E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.092 | TFLOPs: 64.27 | +[default7]: iteration 2703/ 3814 | consumed samples: 1383936 | consumed tokens: 2834300928 | elapsed time per iteration (s): 5.92 | learning rate: 1.218E-04 | global batch size: 512 | lm loss: 3.347997E+00 | loss scale: 131072.0 | grad norm: 0.135 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.494 | TFLOPs: 65.33 | +[default7]: iteration 2704/ 3814 | consumed samples: 1384448 | consumed tokens: 2835349504 | elapsed time per iteration (s): 6.01 | learning rate: 1.216E-04 | global batch size: 512 | lm loss: 3.316453E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.152 | TFLOPs: 64.32 | +[default7]: iteration 2705/ 3814 | consumed samples: 1384960 | consumed tokens: 2836398080 | elapsed time per iteration (s): 6.14 | learning rate: 1.214E-04 | global batch size: 512 | lm loss: 3.313617E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.358 | TFLOPs: 62.96 | +[default7]: iteration 2706/ 3814 | consumed samples: 1385472 | consumed tokens: 2837446656 | elapsed time per iteration (s): 6.15 | learning rate: 1.212E-04 | global batch size: 512 | lm loss: 3.321657E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.218 | TFLOPs: 62.86 | +[default7]: iteration 2707/ 3814 | consumed samples: 1385984 | consumed tokens: 2838495232 | elapsed time per iteration (s): 6.05 | learning rate: 1.210E-04 | global batch size: 512 | lm loss: 3.331658E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.681 | TFLOPs: 63.96 | +[default7]: iteration 2708/ 3814 | consumed samples: 1386496 | consumed tokens: 2839543808 | elapsed time per iteration (s): 6.00 | learning rate: 1.208E-04 | global batch size: 512 | lm loss: 3.314118E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.346 | TFLOPs: 64.46 | +[default7]: iteration 2709/ 3814 | consumed samples: 1387008 | consumed tokens: 2840592384 | elapsed time per iteration (s): 6.11 | learning rate: 1.206E-04 | global batch size: 512 | lm loss: 3.339545E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.729 | TFLOPs: 63.24 | +[default7]: iteration 2710/ 3814 | consumed samples: 1387520 | consumed tokens: 2841640960 | elapsed time per iteration (s): 6.16 | learning rate: 1.204E-04 | global batch size: 512 | lm loss: 3.321804E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.119 | TFLOPs: 62.78 | +[default7]: iteration 2711/ 3814 | consumed samples: 1388032 | consumed tokens: 2842689536 | elapsed time per iteration (s): 6.21 | learning rate: 1.202E-04 | global batch size: 512 | lm loss: 3.352682E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.491 | TFLOPs: 62.31 | +[default7]: iteration 2712/ 3814 | consumed samples: 1388544 | consumed tokens: 2843738112 | elapsed time per iteration (s): 6.15 | learning rate: 1.200E-04 | global batch size: 512 | lm loss: 3.326684E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.262 | TFLOPs: 62.89 | +[default7]: iteration 2713/ 3814 | consumed samples: 1389056 | consumed tokens: 2844786688 | elapsed time per iteration (s): 6.15 | learning rate: 1.198E-04 | global batch size: 512 | lm loss: 3.313171E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.228 | TFLOPs: 62.86 | +[default7]: iteration 2714/ 3814 | consumed samples: 1389568 | consumed tokens: 2845835264 | elapsed time per iteration (s): 5.91 | learning rate: 1.196E-04 | global batch size: 512 | lm loss: 3.360197E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.696 | TFLOPs: 65.48 | +[default7]: iteration 2715/ 3814 | consumed samples: 1390080 | consumed tokens: 2846883840 | elapsed time per iteration (s): 6.12 | learning rate: 1.194E-04 | global batch size: 512 | lm loss: 3.314658E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.602 | TFLOPs: 63.15 | +[default7]: iteration 2716/ 3814 | consumed samples: 1390592 | consumed tokens: 2847932416 | elapsed time per iteration (s): 6.15 | learning rate: 1.192E-04 | global batch size: 512 | lm loss: 3.333715E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.193 | TFLOPs: 62.84 | +[default7]: iteration 2717/ 3814 | consumed samples: 1391104 | consumed tokens: 2848980992 | elapsed time per iteration (s): 6.14 | learning rate: 1.190E-04 | global batch size: 512 | lm loss: 3.306085E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.391 | TFLOPs: 62.99 | +[default7]: iteration 2718/ 3814 | consumed samples: 1391616 | consumed tokens: 2850029568 | elapsed time per iteration (s): 5.94 | learning rate: 1.188E-04 | global batch size: 512 | lm loss: 3.300837E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.183 | TFLOPs: 65.09 | +[default7]: iteration 2719/ 3814 | consumed samples: 1392128 | consumed tokens: 2851078144 | elapsed time per iteration (s): 5.98 | learning rate: 1.186E-04 | global batch size: 512 | lm loss: 3.321107E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.548 | TFLOPs: 64.62 | +[default7]: iteration 2720/ 3814 | consumed samples: 1392640 | consumed tokens: 2852126720 | elapsed time per iteration (s): 6.13 | learning rate: 1.184E-04 | global batch size: 512 | lm loss: 3.307399E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.547 | TFLOPs: 63.10 | +[default7]: iteration 2721/ 3814 | consumed samples: 1393152 | consumed tokens: 2853175296 | elapsed time per iteration (s): 6.15 | learning rate: 1.182E-04 | global batch size: 512 | lm loss: 3.349260E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.284 | TFLOPs: 62.91 | +[default7]: iteration 2722/ 3814 | consumed samples: 1393664 | consumed tokens: 2854223872 | elapsed time per iteration (s): 6.17 | learning rate: 1.180E-04 | global batch size: 512 | lm loss: 3.291524E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.958 | TFLOPs: 62.66 | +[default7]: iteration 2723/ 3814 | consumed samples: 1394176 | consumed tokens: 2855272448 | elapsed time per iteration (s): 6.03 | learning rate: 1.178E-04 | global batch size: 512 | lm loss: 3.345609E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.840 | TFLOPs: 64.08 | +[default7]: iteration 2724/ 3814 | consumed samples: 1394688 | consumed tokens: 2856321024 | elapsed time per iteration (s): 6.02 | learning rate: 1.176E-04 | global batch size: 512 | lm loss: 3.295666E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.048 | TFLOPs: 64.24 | +[default7]: iteration 2725/ 3814 | consumed samples: 1395200 | consumed tokens: 2857369600 | elapsed time per iteration (s): 5.97 | learning rate: 1.174E-04 | global batch size: 512 | lm loss: 3.308073E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.711 | TFLOPs: 64.74 | +[default7]: iteration 2726/ 3814 | consumed samples: 1395712 | consumed tokens: 2858418176 | elapsed time per iteration (s): 5.98 | learning rate: 1.172E-04 | global batch size: 512 | lm loss: 3.322631E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.635 | TFLOPs: 64.68 | +[default7]: iteration 2727/ 3814 | consumed samples: 1396224 | consumed tokens: 2859466752 | elapsed time per iteration (s): 6.00 | learning rate: 1.170E-04 | global batch size: 512 | lm loss: 3.320690E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.345 | TFLOPs: 64.46 | +[default7]: iteration 2728/ 3814 | consumed samples: 1396736 | consumed tokens: 2860515328 | elapsed time per iteration (s): 5.93 | learning rate: 1.168E-04 | global batch size: 512 | lm loss: 3.318947E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.298 | TFLOPs: 65.18 | +[default7]: iteration 2729/ 3814 | consumed samples: 1397248 | consumed tokens: 2861563904 | elapsed time per iteration (s): 6.03 | learning rate: 1.166E-04 | global batch size: 512 | lm loss: 3.320068E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.967 | TFLOPs: 64.18 | +[default7]: iteration 2730/ 3814 | consumed samples: 1397760 | consumed tokens: 2862612480 | elapsed time per iteration (s): 5.91 | learning rate: 1.164E-04 | global batch size: 512 | lm loss: 3.338017E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.632 | TFLOPs: 65.43 | +[default7]: iteration 2731/ 3814 | consumed samples: 1398272 | consumed tokens: 2863661056 | elapsed time per iteration (s): 5.97 | learning rate: 1.162E-04 | global batch size: 512 | lm loss: 3.316812E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.693 | TFLOPs: 64.72 | +[default7]: iteration 2732/ 3814 | consumed samples: 1398784 | consumed tokens: 2864709632 | elapsed time per iteration (s): 6.02 | learning rate: 1.160E-04 | global batch size: 512 | lm loss: 3.308917E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.026 | TFLOPs: 64.22 | +[default7]: iteration 2733/ 3814 | consumed samples: 1399296 | consumed tokens: 2865758208 | elapsed time per iteration (s): 5.94 | learning rate: 1.158E-04 | global batch size: 512 | lm loss: 3.330053E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.258 | TFLOPs: 65.15 | +[default7]: iteration 2734/ 3814 | consumed samples: 1399808 | consumed tokens: 2866806784 | elapsed time per iteration (s): 6.09 | learning rate: 1.156E-04 | global batch size: 512 | lm loss: 3.311296E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.027 | TFLOPs: 63.47 | +[default7]: iteration 2735/ 3814 | consumed samples: 1400320 | consumed tokens: 2867855360 | elapsed time per iteration (s): 6.04 | learning rate: 1.154E-04 | global batch size: 512 | lm loss: 3.319928E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.816 | TFLOPs: 64.06 | +[default7]: iteration 2736/ 3814 | consumed samples: 1400832 | consumed tokens: 2868903936 | elapsed time per iteration (s): 6.01 | learning rate: 1.152E-04 | global batch size: 512 | lm loss: 3.356181E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.214 | TFLOPs: 64.36 | +[default7]: iteration 2737/ 3814 | consumed samples: 1401344 | consumed tokens: 2869952512 | elapsed time per iteration (s): 6.04 | learning rate: 1.150E-04 | global batch size: 512 | lm loss: 3.310281E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.735 | TFLOPs: 64.00 | +[default7]: iteration 2738/ 3814 | consumed samples: 1401856 | consumed tokens: 2871001088 | elapsed time per iteration (s): 5.99 | learning rate: 1.148E-04 | global batch size: 512 | lm loss: 3.324061E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.423 | TFLOPs: 64.52 | +[default7]: iteration 2739/ 3814 | consumed samples: 1402368 | consumed tokens: 2872049664 | elapsed time per iteration (s): 5.92 | learning rate: 1.146E-04 | global batch size: 512 | lm loss: 3.334055E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.543 | TFLOPs: 65.37 | +[default7]: iteration 2740/ 3814 | consumed samples: 1402880 | consumed tokens: 2873098240 | elapsed time per iteration (s): 6.01 | learning rate: 1.144E-04 | global batch size: 512 | lm loss: 3.322673E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.222 | TFLOPs: 64.37 | +[default7]: iteration 2741/ 3814 | consumed samples: 1403392 | consumed tokens: 2874146816 | elapsed time per iteration (s): 6.03 | learning rate: 1.143E-04 | global batch size: 512 | lm loss: 3.298808E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.857 | TFLOPs: 64.09 | +[default7]: iteration 2742/ 3814 | consumed samples: 1403904 | consumed tokens: 2875195392 | elapsed time per iteration (s): 5.99 | learning rate: 1.141E-04 | global batch size: 512 | lm loss: 3.324180E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.442 | TFLOPs: 64.54 | +[default7]: iteration 2743/ 3814 | consumed samples: 1404416 | consumed tokens: 2876243968 | elapsed time per iteration (s): 5.99 | learning rate: 1.139E-04 | global batch size: 512 | lm loss: 3.275164E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.472 | TFLOPs: 64.56 | +[default7]: iteration 2744/ 3814 | consumed samples: 1404928 | consumed tokens: 2877292544 | elapsed time per iteration (s): 6.05 | learning rate: 1.137E-04 | global batch size: 512 | lm loss: 3.315356E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.600 | TFLOPs: 63.90 | +[default7]: iteration 2745/ 3814 | consumed samples: 1405440 | consumed tokens: 2878341120 | elapsed time per iteration (s): 6.00 | learning rate: 1.135E-04 | global batch size: 512 | lm loss: 3.324467E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.282 | TFLOPs: 64.41 | +[default7]: iteration 2746/ 3814 | consumed samples: 1405952 | consumed tokens: 2879389696 | elapsed time per iteration (s): 6.00 | learning rate: 1.133E-04 | global batch size: 512 | lm loss: 3.310797E+00 | loss scale: 131072.0 | grad norm: 0.133 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.339 | TFLOPs: 64.46 | +[default7]: iteration 2747/ 3814 | consumed samples: 1406464 | consumed tokens: 2880438272 | elapsed time per iteration (s): 6.00 | learning rate: 1.131E-04 | global batch size: 512 | lm loss: 3.340200E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.299 | TFLOPs: 64.43 | +[default7]: iteration 2748/ 3814 | consumed samples: 1406976 | consumed tokens: 2881486848 | elapsed time per iteration (s): 5.98 | learning rate: 1.129E-04 | global batch size: 512 | lm loss: 3.330450E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.598 | TFLOPs: 64.65 | +[default7]: iteration 2749/ 3814 | consumed samples: 1407488 | consumed tokens: 2882535424 | elapsed time per iteration (s): 5.97 | learning rate: 1.127E-04 | global batch size: 512 | lm loss: 3.326878E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.759 | TFLOPs: 64.77 | +[default7]: iteration 2750/ 3814 | consumed samples: 1408000 | consumed tokens: 2883584000 | elapsed time per iteration (s): 6.02 | learning rate: 1.125E-04 | global batch size: 512 | lm loss: 3.313727E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.071 | TFLOPs: 64.25 | +[default1]:[2023-02-16 12:08:34,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_01-model_states.pt... +[default0]:saving checkpoint at iteration 2750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default0]:[2023-02-16 12:08:34,507] [INFO] [logging.py:68:log_dist] [Rank 0] [Torch] Checkpoint global_step2750 is begin to save! +[default0]:[2023-02-16 12:08:34,511] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:34,664] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:34,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:34,656] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_01-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,656] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:34,711] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,712] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:34,720] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_04-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:34,721] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:34,779] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:34,779] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:34,769] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_05-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,770] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:34,822] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,823] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:34,835] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_06-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:34,836] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:34,890] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:34,891] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:34,878] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_07-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,878] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:34,933] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,934] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:34,961] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_08-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:34,962] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:34,996] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:34,997] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,017] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_09-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,017] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,072] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,072] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,050] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_10-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,051] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,105] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,105] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,130] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_11-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,131] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,186] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,187] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_12-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,160] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,213] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,246] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_13-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,247] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,271] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,332] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_14-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,309] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,365] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_15-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,366] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,388] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,389] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,427] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_16-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,428] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,491] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,491] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,449] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_17-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,450] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,503] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,503] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,546] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_18-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,547] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,556] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,557] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,612] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,612] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,603] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_19-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,604] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,665] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_20-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,665] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,669] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,670] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,726] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,727] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,722] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_21-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,723] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_22-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,780] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,780] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,781] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,863] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_23-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,864] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,860] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,860] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:35,913] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,913] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:35,921] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_24-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,921] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:35,977] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_25-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:35,977] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:35,967] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:35,967] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:36,020] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,021] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:36,033] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_26-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,034] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:36,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_27-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,098] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:36,075] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,076] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:36,131] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,132] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:36,157] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_28-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,157] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:36,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,190] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:36,214] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_29-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,214] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:36,280] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_30-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,281] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:36,252] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,253] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:36,306] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,307] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:36,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_31-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,336] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:36,402] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_32-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,402] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:36,360] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,361] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:36,431] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,431] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_01-model_states.pt... +[default0]:[2023-02-16 12:08:36,459] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_33-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,460] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_00-model_states.pt... +[default1]:[2023-02-16 12:08:36,485] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,485] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_01-model_states.pt... +[default1]:[2023-02-16 12:08:36,486] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_01-model_states.pt. +[default1]:[2023-02-16 12:08:36,487] [INFO] [logging.py:68:log_dist] [Rank 1] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_01_model_states.pt +[default1]:[2023-02-16 12:08:36,487] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_01_model_states.pt... +[default1]:[2023-02-16 12:08:36,490] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_01_model_states.pt. +[default0]:[2023-02-16 12:08:36,515] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_34-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,515] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:36,569] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_35-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,569] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_00-model_states.pt... +[default0]:[2023-02-16 12:08:36,570] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/layer_37-model_00-model_states.pt. +[default0]:[2023-02-16 12:08:36,571] [INFO] [logging.py:68:log_dist] [Rank 0] Saving model checkpoint: /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_00_model_states.pt +[default0]:[2023-02-16 12:08:36,571] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_00_model_states.pt... +[default0]:[2023-02-16 12:08:36,573] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/mp_rank_00_model_states.pt. +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_00_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_01_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_00_optim_states.pt... +[default0]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_01_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_01_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_00_optim_states.pt... +[default1]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_01_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_01_optim_states.pt... +[default3]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_00_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_01_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_00_optim_states.pt... +[default2]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_01_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_00_optim_states.pt... +[default6]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_00_optim_states.pt... +[default5]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_01_optim_states.pt... +[default4]:[2023-02-16 12:08:36,600] [INFO] [torch_checkpoint_engine.py:15:save] [Torch] Saving /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_00_optim_states.pt... +[default7]:[2023-02-16 12:08:37,082] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,082] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,082] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,109] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,109] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,109] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,120] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,120] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_23_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,120] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,097] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,097] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,097] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,146] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,146] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,146] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,160] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,160] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,160] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,132] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,132] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_7_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,133] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,116] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,116] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,116] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,159] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,193] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,195] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,195] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,176] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,176] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,176] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,136] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,136] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,136] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,138] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,139] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,139] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,229] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,229] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,230] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,175] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,175] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,175] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,249] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,249] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_0_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,250] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,159] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,159] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,159] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,212] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,212] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_21_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,212] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,188] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,188] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,188] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,221] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,221] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_16_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,221] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,228] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,229] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_3_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,229] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,158] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,158] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_2_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,158] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,196] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,196] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,196] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,189] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,189] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_20_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,189] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,178] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,178] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,178] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,254] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,254] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,254] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,260] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_5_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,266] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_12_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,266] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,256] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,256] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_13_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,256] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,211] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,211] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_22_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,211] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,217] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,217] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,218] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,270] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,270] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,270] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,222] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,222] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_1_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,222] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,247] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,247] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,247] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,219] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,219] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_6_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,219] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,308] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,308] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,308] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,260] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,260] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,260] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,267] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,299] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,299] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,299] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,266] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,267] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_28_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,294] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,294] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_29_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,286] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_18_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,279] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,279] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_19_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,279] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,281] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,281] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_9_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,281] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,293] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,294] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,294] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,337] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,337] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,337] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,267] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,267] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_15_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,267] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,331] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,332] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_24_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,332] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]:[2023-02-16 12:08:37,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_00_optim_states.pt. +[default0]:[2023-02-16 12:08:37,286] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_4_mp_rank_00_optim_states.pt +[default0]:[2023-02-16 12:08:37,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,335] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,335] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,336] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,286] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,286] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_10_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,286] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,285] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,285] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_14_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,285] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,311] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,311] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_11_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,311] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default3]:[2023-02-16 12:08:37,340] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_01_optim_states.pt. +[default3]:[2023-02-16 12:08:37,340] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_17_mp_rank_01_optim_states.pt +[default3]:[2023-02-16 12:08:37,340] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default2]:[2023-02-16 12:08:37,348] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_00_optim_states.pt. +[default2]:[2023-02-16 12:08:37,348] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_25_mp_rank_00_optim_states.pt +[default2]:[2023-02-16 12:08:37,349] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default1]:[2023-02-16 12:08:37,379] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_01_optim_states.pt. +[default1]:[2023-02-16 12:08:37,379] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_8_mp_rank_01_optim_states.pt +[default1]:[2023-02-16 12:08:37,379] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,422] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,422] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,422] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,487] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,487] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_27_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,487] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,554] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,554] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,554] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default6]:[2023-02-16 12:08:37,521] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_00_optim_states.pt. +[default6]:[2023-02-16 12:08:37,521] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_00_optim_states.pt +[default6]:[2023-02-16 12:08:37,521] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:[2023-02-16 12:08:37,526] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_01_optim_states.pt. +[default7]:[2023-02-16 12:08:37,527] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_31_mp_rank_01_optim_states.pt +[default7]:[2023-02-16 12:08:37,527] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default5]:[2023-02-16 12:08:37,587] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,588] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_30_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,588] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default4]:[2023-02-16 12:08:37,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_00_optim_states.pt. +[default4]:[2023-02-16 12:08:37,618] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_00_optim_states.pt +[default4]:[2023-02-16 12:08:37,619] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default7]:time (ms) | save-checkpoint: 3114.25 +[default5]:[2023-02-16 12:08:37,618] [INFO] [torch_checkpoint_engine.py:17:save] [Torch] Saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_01_optim_states.pt. +[default5]:[2023-02-16 12:08:37,618] [INFO] [engine.py:3199:_save_zero_checkpoint] zero checkpoint saved /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main/global_step2750/zero_pp_rank_26_mp_rank_01_optim_states.pt +[default5]:[2023-02-16 12:08:37,618] [INFO] [torch_checkpoint_engine.py:27:commit] [Torch] Checkpoint global_step2750 is ready now! +[default0]: successfully saved checkpoint at iteration 2750 to /gpfsscratch/rech/ajs/commun/checkpoints/tr14-2B7-lr0.0052-init0.1-inpm10-outm10-atnm10-mup/checkpoints/main +[default7]: iteration 2751/ 3814 | consumed samples: 1408512 | consumed tokens: 2884632576 | elapsed time per iteration (s): 9.11 | learning rate: 1.123E-04 | global batch size: 512 | lm loss: 3.312380E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 56.199 | TFLOPs: 42.45 | +[default7]: iteration 2752/ 3814 | consumed samples: 1409024 | consumed tokens: 2885681152 | elapsed time per iteration (s): 6.01 | learning rate: 1.121E-04 | global batch size: 512 | lm loss: 3.321072E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.228 | TFLOPs: 64.37 | +[default7]: iteration 2753/ 3814 | consumed samples: 1409536 | consumed tokens: 2886729728 | elapsed time per iteration (s): 6.00 | learning rate: 1.119E-04 | global batch size: 512 | lm loss: 3.315271E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.295 | TFLOPs: 64.42 | +[default7]: iteration 2754/ 3814 | consumed samples: 1410048 | consumed tokens: 2887778304 | elapsed time per iteration (s): 5.91 | learning rate: 1.117E-04 | global batch size: 512 | lm loss: 3.331166E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.572 | TFLOPs: 65.39 | +[default7]: iteration 2755/ 3814 | consumed samples: 1410560 | consumed tokens: 2888826880 | elapsed time per iteration (s): 6.01 | learning rate: 1.115E-04 | global batch size: 512 | lm loss: 3.303688E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.226 | TFLOPs: 64.37 | +[default7]: iteration 2756/ 3814 | consumed samples: 1411072 | consumed tokens: 2889875456 | elapsed time per iteration (s): 5.99 | learning rate: 1.113E-04 | global batch size: 512 | lm loss: 3.302180E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.447 | TFLOPs: 64.54 | +[default7]: iteration 2757/ 3814 | consumed samples: 1411584 | consumed tokens: 2890924032 | elapsed time per iteration (s): 5.94 | learning rate: 1.111E-04 | global batch size: 512 | lm loss: 3.324097E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.181 | TFLOPs: 65.09 | +[default7]: iteration 2758/ 3814 | consumed samples: 1412096 | consumed tokens: 2891972608 | elapsed time per iteration (s): 5.95 | learning rate: 1.109E-04 | global batch size: 512 | lm loss: 3.282692E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.058 | TFLOPs: 65.00 | +[default7]: iteration 2759/ 3814 | consumed samples: 1412608 | consumed tokens: 2893021184 | elapsed time per iteration (s): 6.05 | learning rate: 1.107E-04 | global batch size: 512 | lm loss: 3.348338E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.568 | TFLOPs: 63.87 | +[default7]: iteration 2760/ 3814 | consumed samples: 1413120 | consumed tokens: 2894069760 | elapsed time per iteration (s): 6.00 | learning rate: 1.106E-04 | global batch size: 512 | lm loss: 3.311067E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.391 | TFLOPs: 64.50 | +[default7]: iteration 2761/ 3814 | consumed samples: 1413632 | consumed tokens: 2895118336 | elapsed time per iteration (s): 6.13 | learning rate: 1.104E-04 | global batch size: 512 | lm loss: 3.334956E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.517 | TFLOPs: 63.08 | +[default7]: iteration 2762/ 3814 | consumed samples: 1414144 | consumed tokens: 2896166912 | elapsed time per iteration (s): 6.08 | learning rate: 1.102E-04 | global batch size: 512 | lm loss: 3.330746E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.168 | TFLOPs: 63.57 | +[default7]: iteration 2763/ 3814 | consumed samples: 1414656 | consumed tokens: 2897215488 | elapsed time per iteration (s): 6.10 | learning rate: 1.100E-04 | global batch size: 512 | lm loss: 3.290831E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.875 | TFLOPs: 63.35 | +[default7]: iteration 2764/ 3814 | consumed samples: 1415168 | consumed tokens: 2898264064 | elapsed time per iteration (s): 6.17 | learning rate: 1.098E-04 | global batch size: 512 | lm loss: 3.323942E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.023 | TFLOPs: 62.71 | +[default7]: iteration 2765/ 3814 | consumed samples: 1415680 | consumed tokens: 2899312640 | elapsed time per iteration (s): 6.00 | learning rate: 1.096E-04 | global batch size: 512 | lm loss: 3.306625E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.297 | TFLOPs: 64.43 | +[default7]: iteration 2766/ 3814 | consumed samples: 1416192 | consumed tokens: 2900361216 | elapsed time per iteration (s): 6.12 | learning rate: 1.094E-04 | global batch size: 512 | lm loss: 3.304721E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.604 | TFLOPs: 63.15 | +[default7]: iteration 2767/ 3814 | consumed samples: 1416704 | consumed tokens: 2901409792 | elapsed time per iteration (s): 6.13 | learning rate: 1.092E-04 | global batch size: 512 | lm loss: 3.313751E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.551 | TFLOPs: 63.11 | +[default7]: iteration 2768/ 3814 | consumed samples: 1417216 | consumed tokens: 2902458368 | elapsed time per iteration (s): 6.00 | learning rate: 1.090E-04 | global batch size: 512 | lm loss: 3.338506E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.286 | TFLOPs: 64.42 | +[default7]: iteration 2769/ 3814 | consumed samples: 1417728 | consumed tokens: 2903506944 | elapsed time per iteration (s): 6.14 | learning rate: 1.088E-04 | global batch size: 512 | lm loss: 3.299821E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.385 | TFLOPs: 62.98 | +[default7]: iteration 2770/ 3814 | consumed samples: 1418240 | consumed tokens: 2904555520 | elapsed time per iteration (s): 6.03 | learning rate: 1.086E-04 | global batch size: 512 | lm loss: 3.301671E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.871 | TFLOPs: 64.10 | +[default7]: iteration 2771/ 3814 | consumed samples: 1418752 | consumed tokens: 2905604096 | elapsed time per iteration (s): 5.95 | learning rate: 1.084E-04 | global batch size: 512 | lm loss: 3.331113E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.117 | TFLOPs: 65.04 | +[default7]: iteration 2772/ 3814 | consumed samples: 1419264 | consumed tokens: 2906652672 | elapsed time per iteration (s): 5.96 | learning rate: 1.082E-04 | global batch size: 512 | lm loss: 3.305786E+00 | loss scale: 131072.0 | grad norm: 0.130 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.964 | TFLOPs: 64.93 | +[default7]: iteration 2773/ 3814 | consumed samples: 1419776 | consumed tokens: 2907701248 | elapsed time per iteration (s): 5.99 | learning rate: 1.081E-04 | global batch size: 512 | lm loss: 3.337113E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.500 | TFLOPs: 64.58 | +[default7]: iteration 2774/ 3814 | consumed samples: 1420288 | consumed tokens: 2908749824 | elapsed time per iteration (s): 5.89 | learning rate: 1.079E-04 | global batch size: 512 | lm loss: 3.331791E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.869 | TFLOPs: 65.61 | +[default7]: iteration 2775/ 3814 | consumed samples: 1420800 | consumed tokens: 2909798400 | elapsed time per iteration (s): 6.09 | learning rate: 1.077E-04 | global batch size: 512 | lm loss: 3.288485E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.108 | TFLOPs: 63.53 | +[default7]: iteration 2776/ 3814 | consumed samples: 1421312 | consumed tokens: 2910846976 | elapsed time per iteration (s): 6.11 | learning rate: 1.075E-04 | global batch size: 512 | lm loss: 3.310893E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.758 | TFLOPs: 63.26 | +[default7]: iteration 2777/ 3814 | consumed samples: 1421824 | consumed tokens: 2911895552 | elapsed time per iteration (s): 6.01 | learning rate: 1.073E-04 | global batch size: 512 | lm loss: 3.316812E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.143 | TFLOPs: 64.31 | +[default7]: iteration 2778/ 3814 | consumed samples: 1422336 | consumed tokens: 2912944128 | elapsed time per iteration (s): 6.02 | learning rate: 1.071E-04 | global batch size: 512 | lm loss: 3.346298E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.089 | TFLOPs: 64.27 | +[default7]: iteration 2779/ 3814 | consumed samples: 1422848 | consumed tokens: 2913992704 | elapsed time per iteration (s): 5.99 | learning rate: 1.069E-04 | global batch size: 512 | lm loss: 3.313870E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.517 | TFLOPs: 64.59 | +[default7]: iteration 2780/ 3814 | consumed samples: 1423360 | consumed tokens: 2915041280 | elapsed time per iteration (s): 5.94 | learning rate: 1.067E-04 | global batch size: 512 | lm loss: 3.323208E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.251 | TFLOPs: 65.15 | +[default7]: iteration 2781/ 3814 | consumed samples: 1423872 | consumed tokens: 2916089856 | elapsed time per iteration (s): 6.00 | learning rate: 1.065E-04 | global batch size: 512 | lm loss: 3.329265E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.355 | TFLOPs: 64.47 | +[default7]: iteration 2782/ 3814 | consumed samples: 1424384 | consumed tokens: 2917138432 | elapsed time per iteration (s): 6.04 | learning rate: 1.063E-04 | global batch size: 512 | lm loss: 3.289578E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.766 | TFLOPs: 64.02 | +[default7]: iteration 2783/ 3814 | consumed samples: 1424896 | consumed tokens: 2918187008 | elapsed time per iteration (s): 6.16 | learning rate: 1.061E-04 | global batch size: 512 | lm loss: 3.274760E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.120 | TFLOPs: 62.78 | +[default7]: iteration 2784/ 3814 | consumed samples: 1425408 | consumed tokens: 2919235584 | elapsed time per iteration (s): 6.12 | learning rate: 1.060E-04 | global batch size: 512 | lm loss: 3.309430E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.658 | TFLOPs: 63.19 | +[default7]: iteration 2785/ 3814 | consumed samples: 1425920 | consumed tokens: 2920284160 | elapsed time per iteration (s): 6.07 | learning rate: 1.058E-04 | global batch size: 512 | lm loss: 3.313392E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.345 | TFLOPs: 63.71 | +[default7]: iteration 2786/ 3814 | consumed samples: 1426432 | consumed tokens: 2921332736 | elapsed time per iteration (s): 6.00 | learning rate: 1.056E-04 | global batch size: 512 | lm loss: 3.316551E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.361 | TFLOPs: 64.47 | +[default7]: iteration 2787/ 3814 | consumed samples: 1426944 | consumed tokens: 2922381312 | elapsed time per iteration (s): 6.09 | learning rate: 1.054E-04 | global batch size: 512 | lm loss: 3.309661E+00 | loss scale: 131072.0 | grad norm: 0.137 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.042 | TFLOPs: 63.48 | +[default7]: iteration 2788/ 3814 | consumed samples: 1427456 | consumed tokens: 2923429888 | elapsed time per iteration (s): 6.10 | learning rate: 1.052E-04 | global batch size: 512 | lm loss: 3.306585E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.879 | TFLOPs: 63.35 | +[default7]: iteration 2789/ 3814 | consumed samples: 1427968 | consumed tokens: 2924478464 | elapsed time per iteration (s): 6.07 | learning rate: 1.050E-04 | global batch size: 512 | lm loss: 3.341831E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.397 | TFLOPs: 63.75 | +[default7]: iteration 2790/ 3814 | consumed samples: 1428480 | consumed tokens: 2925527040 | elapsed time per iteration (s): 5.95 | learning rate: 1.048E-04 | global batch size: 512 | lm loss: 3.298311E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.076 | TFLOPs: 65.01 | +[default7]: iteration 2791/ 3814 | consumed samples: 1428992 | consumed tokens: 2926575616 | elapsed time per iteration (s): 6.09 | learning rate: 1.046E-04 | global batch size: 512 | lm loss: 3.336294E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.080 | TFLOPs: 63.51 | +[default7]: iteration 2792/ 3814 | consumed samples: 1429504 | consumed tokens: 2927624192 | elapsed time per iteration (s): 5.99 | learning rate: 1.044E-04 | global batch size: 512 | lm loss: 3.304921E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.457 | TFLOPs: 64.55 | +[default7]: iteration 2793/ 3814 | consumed samples: 1430016 | consumed tokens: 2928672768 | elapsed time per iteration (s): 6.05 | learning rate: 1.042E-04 | global batch size: 512 | lm loss: 3.320014E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.624 | TFLOPs: 63.92 | +[default7]: iteration 2794/ 3814 | consumed samples: 1430528 | consumed tokens: 2929721344 | elapsed time per iteration (s): 6.11 | learning rate: 1.041E-04 | global batch size: 512 | lm loss: 3.356929E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.844 | TFLOPs: 63.33 | +[default7]: iteration 2795/ 3814 | consumed samples: 1431040 | consumed tokens: 2930769920 | elapsed time per iteration (s): 6.02 | learning rate: 1.039E-04 | global batch size: 512 | lm loss: 3.289096E+00 | loss scale: 131072.0 | grad norm: 0.134 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.031 | TFLOPs: 64.22 | +[default7]: iteration 2796/ 3814 | consumed samples: 1431552 | consumed tokens: 2931818496 | elapsed time per iteration (s): 6.01 | learning rate: 1.037E-04 | global batch size: 512 | lm loss: 3.288366E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.130 | TFLOPs: 64.30 | +[default7]: iteration 2797/ 3814 | consumed samples: 1432064 | consumed tokens: 2932867072 | elapsed time per iteration (s): 6.05 | learning rate: 1.035E-04 | global batch size: 512 | lm loss: 3.302180E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.603 | TFLOPs: 63.90 | +[default7]: iteration 2798/ 3814 | consumed samples: 1432576 | consumed tokens: 2933915648 | elapsed time per iteration (s): 6.06 | learning rate: 1.033E-04 | global batch size: 512 | lm loss: 3.293722E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.533 | TFLOPs: 63.85 | +[default7]: iteration 2799/ 3814 | consumed samples: 1433088 | consumed tokens: 2934964224 | elapsed time per iteration (s): 6.05 | learning rate: 1.031E-04 | global batch size: 512 | lm loss: 3.325072E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.627 | TFLOPs: 63.92 | +[default7]: iteration 2800/ 3814 | consumed samples: 1433600 | consumed tokens: 2936012800 | elapsed time per iteration (s): 6.04 | learning rate: 1.029E-04 | global batch size: 512 | lm loss: 3.322627E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.787 | TFLOPs: 64.04 | +[default7]: iteration 2801/ 3814 | consumed samples: 1434112 | consumed tokens: 2937061376 | elapsed time per iteration (s): 6.01 | learning rate: 1.027E-04 | global batch size: 512 | lm loss: 3.293145E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.161 | TFLOPs: 64.32 | +[default7]: iteration 2802/ 3814 | consumed samples: 1434624 | consumed tokens: 2938109952 | elapsed time per iteration (s): 6.06 | learning rate: 1.025E-04 | global batch size: 512 | lm loss: 3.311032E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.425 | TFLOPs: 63.77 | +[default7]: iteration 2803/ 3814 | consumed samples: 1435136 | consumed tokens: 2939158528 | elapsed time per iteration (s): 6.08 | learning rate: 1.024E-04 | global batch size: 512 | lm loss: 3.327368E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.244 | TFLOPs: 63.63 | +[default7]: iteration 2804/ 3814 | consumed samples: 1435648 | consumed tokens: 2940207104 | elapsed time per iteration (s): 6.04 | learning rate: 1.022E-04 | global batch size: 512 | lm loss: 3.318743E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.805 | TFLOPs: 64.05 | +[default7]: iteration 2805/ 3814 | consumed samples: 1436160 | consumed tokens: 2941255680 | elapsed time per iteration (s): 6.03 | learning rate: 1.020E-04 | global batch size: 512 | lm loss: 3.305596E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.921 | TFLOPs: 64.14 | +[default7]: iteration 2806/ 3814 | consumed samples: 1436672 | consumed tokens: 2942304256 | elapsed time per iteration (s): 6.04 | learning rate: 1.018E-04 | global batch size: 512 | lm loss: 3.284484E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.785 | TFLOPs: 64.04 | +[default7]: iteration 2807/ 3814 | consumed samples: 1437184 | consumed tokens: 2943352832 | elapsed time per iteration (s): 6.05 | learning rate: 1.016E-04 | global batch size: 512 | lm loss: 3.300364E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.606 | TFLOPs: 63.90 | +[default7]: iteration 2808/ 3814 | consumed samples: 1437696 | consumed tokens: 2944401408 | elapsed time per iteration (s): 6.09 | learning rate: 1.014E-04 | global batch size: 512 | lm loss: 3.307131E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.083 | TFLOPs: 63.51 | +[default7]: iteration 2809/ 3814 | consumed samples: 1438208 | consumed tokens: 2945449984 | elapsed time per iteration (s): 6.06 | learning rate: 1.012E-04 | global batch size: 512 | lm loss: 3.304881E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.543 | TFLOPs: 63.86 | +[default7]: iteration 2810/ 3814 | consumed samples: 1438720 | consumed tokens: 2946498560 | elapsed time per iteration (s): 6.07 | learning rate: 1.010E-04 | global batch size: 512 | lm loss: 3.302972E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.288 | TFLOPs: 63.66 | +[default7]: iteration 2811/ 3814 | consumed samples: 1439232 | consumed tokens: 2947547136 | elapsed time per iteration (s): 6.05 | learning rate: 1.009E-04 | global batch size: 512 | lm loss: 3.304276E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.614 | TFLOPs: 63.91 | +[default7]: iteration 2812/ 3814 | consumed samples: 1439744 | consumed tokens: 2948595712 | elapsed time per iteration (s): 6.01 | learning rate: 1.007E-04 | global batch size: 512 | lm loss: 3.328799E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.247 | TFLOPs: 64.39 | +[default7]: iteration 2813/ 3814 | consumed samples: 1440256 | consumed tokens: 2949644288 | elapsed time per iteration (s): 6.05 | learning rate: 1.005E-04 | global batch size: 512 | lm loss: 3.328307E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.593 | TFLOPs: 63.89 | +[default7]: iteration 2814/ 3814 | consumed samples: 1440768 | consumed tokens: 2950692864 | elapsed time per iteration (s): 6.06 | learning rate: 1.003E-04 | global batch size: 512 | lm loss: 3.315594E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.479 | TFLOPs: 63.81 | +[default7]: iteration 2815/ 3814 | consumed samples: 1441280 | consumed tokens: 2951741440 | elapsed time per iteration (s): 6.03 | learning rate: 1.001E-04 | global batch size: 512 | lm loss: 3.339646E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.893 | TFLOPs: 64.12 | +[default7]: iteration 2816/ 3814 | consumed samples: 1441792 | consumed tokens: 2952790016 | elapsed time per iteration (s): 6.10 | learning rate: 9.993E-05 | global batch size: 512 | lm loss: 3.287824E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.936 | TFLOPs: 63.40 | +[default7]: iteration 2817/ 3814 | consumed samples: 1442304 | consumed tokens: 2953838592 | elapsed time per iteration (s): 6.06 | learning rate: 9.974E-05 | global batch size: 512 | lm loss: 3.297568E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.547 | TFLOPs: 63.86 | +[default7]: iteration 2818/ 3814 | consumed samples: 1442816 | consumed tokens: 2954887168 | elapsed time per iteration (s): 6.14 | learning rate: 9.955E-05 | global batch size: 512 | lm loss: 3.324720E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.345 | TFLOPs: 62.95 | +[default7]: iteration 2819/ 3814 | consumed samples: 1443328 | consumed tokens: 2955935744 | elapsed time per iteration (s): 6.05 | learning rate: 9.937E-05 | global batch size: 512 | lm loss: 3.305960E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.639 | TFLOPs: 63.93 | +[default7]: iteration 2820/ 3814 | consumed samples: 1443840 | consumed tokens: 2956984320 | elapsed time per iteration (s): 6.09 | learning rate: 9.918E-05 | global batch size: 512 | lm loss: 3.306859E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.011 | TFLOPs: 63.45 | +[default7]: iteration 2821/ 3814 | consumed samples: 1444352 | consumed tokens: 2958032896 | elapsed time per iteration (s): 6.01 | learning rate: 9.900E-05 | global batch size: 512 | lm loss: 3.311473E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.191 | TFLOPs: 64.35 | +[default7]: iteration 2822/ 3814 | consumed samples: 1444864 | consumed tokens: 2959081472 | elapsed time per iteration (s): 6.06 | learning rate: 9.881E-05 | global batch size: 512 | lm loss: 3.318303E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.479 | TFLOPs: 63.81 | +[default7]: iteration 2823/ 3814 | consumed samples: 1445376 | consumed tokens: 2960130048 | elapsed time per iteration (s): 6.07 | learning rate: 9.863E-05 | global batch size: 512 | lm loss: 3.308939E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.306 | TFLOPs: 63.68 | +[default7]: iteration 2824/ 3814 | consumed samples: 1445888 | consumed tokens: 2961178624 | elapsed time per iteration (s): 6.05 | learning rate: 9.844E-05 | global batch size: 512 | lm loss: 3.304499E+00 | loss scale: 131072.0 | grad norm: 0.108 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.635 | TFLOPs: 63.93 | +[default7]: iteration 2825/ 3814 | consumed samples: 1446400 | consumed tokens: 2962227200 | elapsed time per iteration (s): 6.04 | learning rate: 9.826E-05 | global batch size: 512 | lm loss: 3.304224E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.786 | TFLOPs: 64.04 | +[default7]: iteration 2826/ 3814 | consumed samples: 1446912 | consumed tokens: 2963275776 | elapsed time per iteration (s): 6.05 | learning rate: 9.807E-05 | global batch size: 512 | lm loss: 3.300548E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.563 | TFLOPs: 63.87 | +[default7]: iteration 2827/ 3814 | consumed samples: 1447424 | consumed tokens: 2964324352 | elapsed time per iteration (s): 6.09 | learning rate: 9.789E-05 | global batch size: 512 | lm loss: 3.337193E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.060 | TFLOPs: 63.49 | +[default7]: iteration 2828/ 3814 | consumed samples: 1447936 | consumed tokens: 2965372928 | elapsed time per iteration (s): 6.00 | learning rate: 9.770E-05 | global batch size: 512 | lm loss: 3.318784E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.322 | TFLOPs: 64.44 | +[default7]: iteration 2829/ 3814 | consumed samples: 1448448 | consumed tokens: 2966421504 | elapsed time per iteration (s): 6.02 | learning rate: 9.752E-05 | global batch size: 512 | lm loss: 3.328245E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.088 | TFLOPs: 64.27 | +[default7]: iteration 2830/ 3814 | consumed samples: 1448960 | consumed tokens: 2967470080 | elapsed time per iteration (s): 6.00 | learning rate: 9.733E-05 | global batch size: 512 | lm loss: 3.315792E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.326 | TFLOPs: 64.45 | +[default7]: iteration 2831/ 3814 | consumed samples: 1449472 | consumed tokens: 2968518656 | elapsed time per iteration (s): 6.04 | learning rate: 9.715E-05 | global batch size: 512 | lm loss: 3.310959E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.770 | TFLOPs: 64.03 | +[default7]: iteration 2832/ 3814 | consumed samples: 1449984 | consumed tokens: 2969567232 | elapsed time per iteration (s): 6.04 | learning rate: 9.696E-05 | global batch size: 512 | lm loss: 3.309361E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.830 | TFLOPs: 64.07 | +[default7]: iteration 2833/ 3814 | consumed samples: 1450496 | consumed tokens: 2970615808 | elapsed time per iteration (s): 6.01 | learning rate: 9.678E-05 | global batch size: 512 | lm loss: 3.300207E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.125 | TFLOPs: 64.30 | +[default7]: iteration 2834/ 3814 | consumed samples: 1451008 | consumed tokens: 2971664384 | elapsed time per iteration (s): 6.00 | learning rate: 9.660E-05 | global batch size: 512 | lm loss: 3.329158E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.346 | TFLOPs: 64.46 | +[default7]: iteration 2835/ 3814 | consumed samples: 1451520 | consumed tokens: 2972712960 | elapsed time per iteration (s): 5.93 | learning rate: 9.641E-05 | global batch size: 512 | lm loss: 3.298562E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.325 | TFLOPs: 65.20 | +[default7]: iteration 2836/ 3814 | consumed samples: 1452032 | consumed tokens: 2973761536 | elapsed time per iteration (s): 6.00 | learning rate: 9.623E-05 | global batch size: 512 | lm loss: 3.295834E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.404 | TFLOPs: 64.51 | +[default7]: iteration 2837/ 3814 | consumed samples: 1452544 | consumed tokens: 2974810112 | elapsed time per iteration (s): 5.98 | learning rate: 9.605E-05 | global batch size: 512 | lm loss: 3.321740E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.654 | TFLOPs: 64.70 | +[default7]: iteration 2838/ 3814 | consumed samples: 1453056 | consumed tokens: 2975858688 | elapsed time per iteration (s): 5.93 | learning rate: 9.586E-05 | global batch size: 512 | lm loss: 3.276127E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.336 | TFLOPs: 65.21 | +[default7]: iteration 2839/ 3814 | consumed samples: 1453568 | consumed tokens: 2976907264 | elapsed time per iteration (s): 6.03 | learning rate: 9.568E-05 | global batch size: 512 | lm loss: 3.305345E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.937 | TFLOPs: 64.15 | +[default7]: iteration 2840/ 3814 | consumed samples: 1454080 | consumed tokens: 2977955840 | elapsed time per iteration (s): 6.02 | learning rate: 9.550E-05 | global batch size: 512 | lm loss: 3.305510E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.996 | TFLOPs: 64.20 | +[default7]: iteration 2841/ 3814 | consumed samples: 1454592 | consumed tokens: 2979004416 | elapsed time per iteration (s): 6.02 | learning rate: 9.531E-05 | global batch size: 512 | lm loss: 3.323688E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.047 | TFLOPs: 64.24 | +[default7]: iteration 2842/ 3814 | consumed samples: 1455104 | consumed tokens: 2980052992 | elapsed time per iteration (s): 5.98 | learning rate: 9.513E-05 | global batch size: 512 | lm loss: 3.320300E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.570 | TFLOPs: 64.63 | +[default7]: iteration 2843/ 3814 | consumed samples: 1455616 | consumed tokens: 2981101568 | elapsed time per iteration (s): 6.01 | learning rate: 9.495E-05 | global batch size: 512 | lm loss: 3.304776E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.133 | TFLOPs: 64.30 | +[default7]: iteration 2844/ 3814 | consumed samples: 1456128 | consumed tokens: 2982150144 | elapsed time per iteration (s): 5.99 | learning rate: 9.477E-05 | global batch size: 512 | lm loss: 3.282360E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.436 | TFLOPs: 64.53 | +[default7]: iteration 2845/ 3814 | consumed samples: 1456640 | consumed tokens: 2983198720 | elapsed time per iteration (s): 6.03 | learning rate: 9.458E-05 | global batch size: 512 | lm loss: 3.299284E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.888 | TFLOPs: 64.12 | +[default7]: iteration 2846/ 3814 | consumed samples: 1457152 | consumed tokens: 2984247296 | elapsed time per iteration (s): 6.02 | learning rate: 9.440E-05 | global batch size: 512 | lm loss: 3.290984E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.045 | TFLOPs: 64.24 | +[default7]: iteration 2847/ 3814 | consumed samples: 1457664 | consumed tokens: 2985295872 | elapsed time per iteration (s): 6.00 | learning rate: 9.422E-05 | global batch size: 512 | lm loss: 3.330175E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.399 | TFLOPs: 64.50 | +[default7]: iteration 2848/ 3814 | consumed samples: 1458176 | consumed tokens: 2986344448 | elapsed time per iteration (s): 6.02 | learning rate: 9.404E-05 | global batch size: 512 | lm loss: 3.325716E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.072 | TFLOPs: 64.26 | +[default7]: iteration 2849/ 3814 | consumed samples: 1458688 | consumed tokens: 2987393024 | elapsed time per iteration (s): 6.01 | learning rate: 9.385E-05 | global batch size: 512 | lm loss: 3.310736E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.191 | TFLOPs: 64.35 | +[default7]: iteration 2850/ 3814 | consumed samples: 1459200 | consumed tokens: 2988441600 | elapsed time per iteration (s): 6.06 | learning rate: 9.367E-05 | global batch size: 512 | lm loss: 3.309879E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.448 | TFLOPs: 63.78 | +[default7]: iteration 2851/ 3814 | consumed samples: 1459712 | consumed tokens: 2989490176 | elapsed time per iteration (s): 5.99 | learning rate: 9.349E-05 | global batch size: 512 | lm loss: 3.301289E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.456 | TFLOPs: 64.55 | +[default7]: iteration 2852/ 3814 | consumed samples: 1460224 | consumed tokens: 2990538752 | elapsed time per iteration (s): 6.06 | learning rate: 9.331E-05 | global batch size: 512 | lm loss: 3.337880E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.505 | TFLOPs: 63.83 | +[default7]: iteration 2853/ 3814 | consumed samples: 1460736 | consumed tokens: 2991587328 | elapsed time per iteration (s): 5.96 | learning rate: 9.313E-05 | global batch size: 512 | lm loss: 3.286794E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.960 | TFLOPs: 64.93 | +[default7]: iteration 2854/ 3814 | consumed samples: 1461248 | consumed tokens: 2992635904 | elapsed time per iteration (s): 5.98 | learning rate: 9.295E-05 | global batch size: 512 | lm loss: 3.287724E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.550 | TFLOPs: 64.62 | +[default7]: iteration 2855/ 3814 | consumed samples: 1461760 | consumed tokens: 2993684480 | elapsed time per iteration (s): 6.02 | learning rate: 9.277E-05 | global batch size: 512 | lm loss: 3.299259E+00 | loss scale: 131072.0 | grad norm: 0.107 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.051 | TFLOPs: 64.24 | +[default7]: iteration 2856/ 3814 | consumed samples: 1462272 | consumed tokens: 2994733056 | elapsed time per iteration (s): 6.01 | learning rate: 9.259E-05 | global batch size: 512 | lm loss: 3.302774E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.245 | TFLOPs: 64.39 | +[default7]: iteration 2857/ 3814 | consumed samples: 1462784 | consumed tokens: 2995781632 | elapsed time per iteration (s): 5.99 | learning rate: 9.241E-05 | global batch size: 512 | lm loss: 3.306018E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.536 | TFLOPs: 64.61 | +[default7]: iteration 2858/ 3814 | consumed samples: 1463296 | consumed tokens: 2996830208 | elapsed time per iteration (s): 6.01 | learning rate: 9.222E-05 | global batch size: 512 | lm loss: 3.305823E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.233 | TFLOPs: 64.38 | +[default7]: iteration 2859/ 3814 | consumed samples: 1463808 | consumed tokens: 2997878784 | elapsed time per iteration (s): 5.98 | learning rate: 9.204E-05 | global batch size: 512 | lm loss: 3.322083E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.617 | TFLOPs: 64.67 | +[default7]: iteration 2860/ 3814 | consumed samples: 1464320 | consumed tokens: 2998927360 | elapsed time per iteration (s): 5.99 | learning rate: 9.186E-05 | global batch size: 512 | lm loss: 3.328403E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.451 | TFLOPs: 64.54 | +[default7]: iteration 2861/ 3814 | consumed samples: 1464832 | consumed tokens: 2999975936 | elapsed time per iteration (s): 5.96 | learning rate: 9.168E-05 | global batch size: 512 | lm loss: 3.328503E+00 | loss scale: 131072.0 | grad norm: 0.126 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.973 | TFLOPs: 64.94 | +[default7]: iteration 2862/ 3814 | consumed samples: 1465344 | consumed tokens: 3001024512 | elapsed time per iteration (s): 6.02 | learning rate: 9.150E-05 | global batch size: 512 | lm loss: 3.236321E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.098 | TFLOPs: 64.28 | +[default7]: iteration 2863/ 3814 | consumed samples: 1465856 | consumed tokens: 3002073088 | elapsed time per iteration (s): 6.04 | learning rate: 9.132E-05 | global batch size: 512 | lm loss: 3.316609E+00 | loss scale: 131072.0 | grad norm: 0.127 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.757 | TFLOPs: 64.02 | +[default7]: iteration 2864/ 3814 | consumed samples: 1466368 | consumed tokens: 3003121664 | elapsed time per iteration (s): 6.02 | learning rate: 9.114E-05 | global batch size: 512 | lm loss: 3.287789E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.073 | TFLOPs: 64.26 | +[default7]: iteration 2865/ 3814 | consumed samples: 1466880 | consumed tokens: 3004170240 | elapsed time per iteration (s): 6.03 | learning rate: 9.096E-05 | global batch size: 512 | lm loss: 3.331106E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.924 | TFLOPs: 64.14 | +[default7]: iteration 2866/ 3814 | consumed samples: 1467392 | consumed tokens: 3005218816 | elapsed time per iteration (s): 6.02 | learning rate: 9.078E-05 | global batch size: 512 | lm loss: 3.289301E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.000 | TFLOPs: 64.20 | +[default7]: iteration 2867/ 3814 | consumed samples: 1467904 | consumed tokens: 3006267392 | elapsed time per iteration (s): 6.01 | learning rate: 9.061E-05 | global batch size: 512 | lm loss: 3.329891E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.141 | TFLOPs: 64.31 | +[default7]: iteration 2868/ 3814 | consumed samples: 1468416 | consumed tokens: 3007315968 | elapsed time per iteration (s): 5.80 | learning rate: 9.043E-05 | global batch size: 512 | lm loss: 3.294486E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 88.333 | TFLOPs: 66.72 | +[default7]: iteration 2869/ 3814 | consumed samples: 1468928 | consumed tokens: 3008364544 | elapsed time per iteration (s): 6.00 | learning rate: 9.025E-05 | global batch size: 512 | lm loss: 3.296115E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.380 | TFLOPs: 64.49 | +[default7]: iteration 2870/ 3814 | consumed samples: 1469440 | consumed tokens: 3009413120 | elapsed time per iteration (s): 6.00 | learning rate: 9.007E-05 | global batch size: 512 | lm loss: 3.288754E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.404 | TFLOPs: 64.51 | +[default7]: iteration 2871/ 3814 | consumed samples: 1469952 | consumed tokens: 3010461696 | elapsed time per iteration (s): 5.98 | learning rate: 8.989E-05 | global batch size: 512 | lm loss: 3.296601E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.668 | TFLOPs: 64.71 | +[default7]: iteration 2872/ 3814 | consumed samples: 1470464 | consumed tokens: 3011510272 | elapsed time per iteration (s): 6.04 | learning rate: 8.971E-05 | global batch size: 512 | lm loss: 3.308864E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.807 | TFLOPs: 64.06 | +[default7]: iteration 2873/ 3814 | consumed samples: 1470976 | consumed tokens: 3012558848 | elapsed time per iteration (s): 6.01 | learning rate: 8.953E-05 | global batch size: 512 | lm loss: 3.327927E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.224 | TFLOPs: 64.37 | +[default7]: iteration 2874/ 3814 | consumed samples: 1471488 | consumed tokens: 3013607424 | elapsed time per iteration (s): 5.94 | learning rate: 8.935E-05 | global batch size: 512 | lm loss: 3.319695E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.239 | TFLOPs: 65.14 | +[default7]: iteration 2875/ 3814 | consumed samples: 1472000 | consumed tokens: 3014656000 | elapsed time per iteration (s): 5.98 | learning rate: 8.918E-05 | global batch size: 512 | lm loss: 3.305453E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.560 | TFLOPs: 64.62 | +[default7]: iteration 2876/ 3814 | consumed samples: 1472512 | consumed tokens: 3015704576 | elapsed time per iteration (s): 6.00 | learning rate: 8.900E-05 | global batch size: 512 | lm loss: 3.316621E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.362 | TFLOPs: 64.48 | +[default7]: iteration 2877/ 3814 | consumed samples: 1473024 | consumed tokens: 3016753152 | elapsed time per iteration (s): 5.99 | learning rate: 8.882E-05 | global batch size: 512 | lm loss: 3.311940E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.546 | TFLOPs: 64.61 | +[default7]: iteration 2878/ 3814 | consumed samples: 1473536 | consumed tokens: 3017801728 | elapsed time per iteration (s): 5.99 | learning rate: 8.864E-05 | global batch size: 512 | lm loss: 3.308462E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.531 | TFLOPs: 64.60 | +[default7]: iteration 2879/ 3814 | consumed samples: 1474048 | consumed tokens: 3018850304 | elapsed time per iteration (s): 6.05 | learning rate: 8.846E-05 | global batch size: 512 | lm loss: 3.277802E+00 | loss scale: 131072.0 | grad norm: 0.129 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.589 | TFLOPs: 63.89 | +[default7]: iteration 2880/ 3814 | consumed samples: 1474560 | consumed tokens: 3019898880 | elapsed time per iteration (s): 6.04 | learning rate: 8.829E-05 | global batch size: 512 | lm loss: 3.314512E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.767 | TFLOPs: 64.03 | +[default7]: iteration 2881/ 3814 | consumed samples: 1475072 | consumed tokens: 3020947456 | elapsed time per iteration (s): 6.03 | learning rate: 8.811E-05 | global batch size: 512 | lm loss: 3.314795E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.864 | TFLOPs: 64.10 | +[default7]: iteration 2882/ 3814 | consumed samples: 1475584 | consumed tokens: 3021996032 | elapsed time per iteration (s): 5.92 | learning rate: 8.793E-05 | global batch size: 512 | lm loss: 3.302662E+00 | loss scale: 131072.0 | grad norm: 0.132 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.530 | TFLOPs: 65.36 | +[default7]: iteration 2883/ 3814 | consumed samples: 1476096 | consumed tokens: 3023044608 | elapsed time per iteration (s): 5.90 | learning rate: 8.776E-05 | global batch size: 512 | lm loss: 3.297841E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.813 | TFLOPs: 65.57 | +[default7]: iteration 2884/ 3814 | consumed samples: 1476608 | consumed tokens: 3024093184 | elapsed time per iteration (s): 6.06 | learning rate: 8.758E-05 | global batch size: 512 | lm loss: 3.309310E+00 | loss scale: 131072.0 | grad norm: 0.131 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.557 | TFLOPs: 63.87 | +[default7]: iteration 2885/ 3814 | consumed samples: 1477120 | consumed tokens: 3025141760 | elapsed time per iteration (s): 5.96 | learning rate: 8.740E-05 | global batch size: 512 | lm loss: 3.309108E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.845 | TFLOPs: 64.84 | +[default7]: iteration 2886/ 3814 | consumed samples: 1477632 | consumed tokens: 3026190336 | elapsed time per iteration (s): 6.02 | learning rate: 8.723E-05 | global batch size: 512 | lm loss: 3.276604E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.101 | TFLOPs: 64.28 | +[default7]: iteration 2887/ 3814 | consumed samples: 1478144 | consumed tokens: 3027238912 | elapsed time per iteration (s): 6.01 | learning rate: 8.705E-05 | global batch size: 512 | lm loss: 3.322520E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.161 | TFLOPs: 64.32 | +[default7]: iteration 2888/ 3814 | consumed samples: 1478656 | consumed tokens: 3028287488 | elapsed time per iteration (s): 5.93 | learning rate: 8.687E-05 | global batch size: 512 | lm loss: 3.305877E+00 | loss scale: 131072.0 | grad norm: 0.138 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.408 | TFLOPs: 65.26 | +[default7]: iteration 2889/ 3814 | consumed samples: 1479168 | consumed tokens: 3029336064 | elapsed time per iteration (s): 5.99 | learning rate: 8.670E-05 | global batch size: 512 | lm loss: 3.288721E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.411 | TFLOPs: 64.51 | +[default7]: iteration 2890/ 3814 | consumed samples: 1479680 | consumed tokens: 3030384640 | elapsed time per iteration (s): 5.93 | learning rate: 8.652E-05 | global batch size: 512 | lm loss: 3.299943E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.373 | TFLOPs: 65.24 | +[default7]: iteration 2891/ 3814 | consumed samples: 1480192 | consumed tokens: 3031433216 | elapsed time per iteration (s): 5.95 | learning rate: 8.634E-05 | global batch size: 512 | lm loss: 3.285103E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.029 | TFLOPs: 64.98 | +[default7]: iteration 2892/ 3814 | consumed samples: 1480704 | consumed tokens: 3032481792 | elapsed time per iteration (s): 5.99 | learning rate: 8.617E-05 | global batch size: 512 | lm loss: 3.308221E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.462 | TFLOPs: 64.55 | +[default7]: iteration 2893/ 3814 | consumed samples: 1481216 | consumed tokens: 3033530368 | elapsed time per iteration (s): 6.01 | learning rate: 8.599E-05 | global batch size: 512 | lm loss: 3.265808E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.121 | TFLOPs: 64.29 | +[default7]: iteration 2894/ 3814 | consumed samples: 1481728 | consumed tokens: 3034578944 | elapsed time per iteration (s): 6.03 | learning rate: 8.582E-05 | global batch size: 512 | lm loss: 3.346197E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.843 | TFLOPs: 64.08 | +[default7]: iteration 2895/ 3814 | consumed samples: 1482240 | consumed tokens: 3035627520 | elapsed time per iteration (s): 6.01 | learning rate: 8.564E-05 | global batch size: 512 | lm loss: 3.310880E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.250 | TFLOPs: 64.39 | +[default7]: iteration 2896/ 3814 | consumed samples: 1482752 | consumed tokens: 3036676096 | elapsed time per iteration (s): 5.95 | learning rate: 8.547E-05 | global batch size: 512 | lm loss: 3.311203E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.008 | TFLOPs: 64.96 | +[default7]: iteration 2897/ 3814 | consumed samples: 1483264 | consumed tokens: 3037724672 | elapsed time per iteration (s): 6.01 | learning rate: 8.529E-05 | global batch size: 512 | lm loss: 3.326795E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.157 | TFLOPs: 64.32 | +[default7]: iteration 2898/ 3814 | consumed samples: 1483776 | consumed tokens: 3038773248 | elapsed time per iteration (s): 6.06 | learning rate: 8.512E-05 | global batch size: 512 | lm loss: 3.277551E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.465 | TFLOPs: 63.80 | +[default7]: iteration 2899/ 3814 | consumed samples: 1484288 | consumed tokens: 3039821824 | elapsed time per iteration (s): 6.02 | learning rate: 8.494E-05 | global batch size: 512 | lm loss: 3.313385E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.089 | TFLOPs: 64.27 | +[default7]: iteration 2900/ 3814 | consumed samples: 1484800 | consumed tokens: 3040870400 | elapsed time per iteration (s): 6.04 | learning rate: 8.477E-05 | global batch size: 512 | lm loss: 3.291846E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.726 | TFLOPs: 63.99 | +[default7]: iteration 2901/ 3814 | consumed samples: 1485312 | consumed tokens: 3041918976 | elapsed time per iteration (s): 5.99 | learning rate: 8.459E-05 | global batch size: 512 | lm loss: 3.315063E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.453 | TFLOPs: 64.54 | +[default7]: iteration 2902/ 3814 | consumed samples: 1485824 | consumed tokens: 3042967552 | elapsed time per iteration (s): 6.01 | learning rate: 8.442E-05 | global batch size: 512 | lm loss: 3.300513E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.167 | TFLOPs: 64.33 | +[default7]: iteration 2903/ 3814 | consumed samples: 1486336 | consumed tokens: 3044016128 | elapsed time per iteration (s): 5.92 | learning rate: 8.424E-05 | global batch size: 512 | lm loss: 3.283111E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.432 | TFLOPs: 65.28 | +[default7]: iteration 2904/ 3814 | consumed samples: 1486848 | consumed tokens: 3045064704 | elapsed time per iteration (s): 5.95 | learning rate: 8.407E-05 | global batch size: 512 | lm loss: 3.280694E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.043 | TFLOPs: 64.99 | +[default7]: iteration 2905/ 3814 | consumed samples: 1487360 | consumed tokens: 3046113280 | elapsed time per iteration (s): 6.02 | learning rate: 8.390E-05 | global batch size: 512 | lm loss: 3.306856E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.102 | TFLOPs: 64.28 | +[default7]: iteration 2906/ 3814 | consumed samples: 1487872 | consumed tokens: 3047161856 | elapsed time per iteration (s): 5.98 | learning rate: 8.372E-05 | global batch size: 512 | lm loss: 3.287851E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.566 | TFLOPs: 64.63 | +[default7]: iteration 2907/ 3814 | consumed samples: 1488384 | consumed tokens: 3048210432 | elapsed time per iteration (s): 5.91 | learning rate: 8.355E-05 | global batch size: 512 | lm loss: 3.320578E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.592 | TFLOPs: 65.40 | +[default7]: iteration 2908/ 3814 | consumed samples: 1488896 | consumed tokens: 3049259008 | elapsed time per iteration (s): 5.92 | learning rate: 8.338E-05 | global batch size: 512 | lm loss: 3.318796E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.424 | TFLOPs: 65.28 | +[default7]: iteration 2909/ 3814 | consumed samples: 1489408 | consumed tokens: 3050307584 | elapsed time per iteration (s): 5.95 | learning rate: 8.320E-05 | global batch size: 512 | lm loss: 3.307367E+00 | loss scale: 131072.0 | grad norm: 0.124 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.048 | TFLOPs: 64.99 | +[default7]: iteration 2910/ 3814 | consumed samples: 1489920 | consumed tokens: 3051356160 | elapsed time per iteration (s): 6.08 | learning rate: 8.303E-05 | global batch size: 512 | lm loss: 3.295772E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.173 | TFLOPs: 63.58 | +[default7]: iteration 2911/ 3814 | consumed samples: 1490432 | consumed tokens: 3052404736 | elapsed time per iteration (s): 6.03 | learning rate: 8.286E-05 | global batch size: 512 | lm loss: 3.294072E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.841 | TFLOPs: 64.08 | +[default7]: iteration 2912/ 3814 | consumed samples: 1490944 | consumed tokens: 3053453312 | elapsed time per iteration (s): 5.92 | learning rate: 8.268E-05 | global batch size: 512 | lm loss: 3.302620E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.500 | TFLOPs: 65.33 | +[default7]: iteration 2913/ 3814 | consumed samples: 1491456 | consumed tokens: 3054501888 | elapsed time per iteration (s): 6.01 | learning rate: 8.251E-05 | global batch size: 512 | lm loss: 3.310284E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.238 | TFLOPs: 64.38 | +[default7]: iteration 2914/ 3814 | consumed samples: 1491968 | consumed tokens: 3055550464 | elapsed time per iteration (s): 6.02 | learning rate: 8.234E-05 | global batch size: 512 | lm loss: 3.283242E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.071 | TFLOPs: 64.26 | +[default7]: iteration 2915/ 3814 | consumed samples: 1492480 | consumed tokens: 3056599040 | elapsed time per iteration (s): 6.04 | learning rate: 8.217E-05 | global batch size: 512 | lm loss: 3.280658E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.699 | TFLOPs: 63.97 | +[default7]: iteration 2916/ 3814 | consumed samples: 1492992 | consumed tokens: 3057647616 | elapsed time per iteration (s): 5.98 | learning rate: 8.199E-05 | global batch size: 512 | lm loss: 3.288372E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.563 | TFLOPs: 64.63 | +[default7]: iteration 2917/ 3814 | consumed samples: 1493504 | consumed tokens: 3058696192 | elapsed time per iteration (s): 5.99 | learning rate: 8.182E-05 | global batch size: 512 | lm loss: 3.310207E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.440 | TFLOPs: 64.53 | +[default7]: iteration 2918/ 3814 | consumed samples: 1494016 | consumed tokens: 3059744768 | elapsed time per iteration (s): 6.03 | learning rate: 8.165E-05 | global batch size: 512 | lm loss: 3.287670E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.963 | TFLOPs: 64.17 | +[default7]: iteration 2919/ 3814 | consumed samples: 1494528 | consumed tokens: 3060793344 | elapsed time per iteration (s): 6.01 | learning rate: 8.148E-05 | global batch size: 512 | lm loss: 3.313594E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.135 | TFLOPs: 64.30 | +[default7]: iteration 2920/ 3814 | consumed samples: 1495040 | consumed tokens: 3061841920 | elapsed time per iteration (s): 6.04 | learning rate: 8.131E-05 | global batch size: 512 | lm loss: 3.283026E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.780 | TFLOPs: 64.04 | +[default7]: iteration 2921/ 3814 | consumed samples: 1495552 | consumed tokens: 3062890496 | elapsed time per iteration (s): 6.06 | learning rate: 8.113E-05 | global batch size: 512 | lm loss: 3.321990E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.444 | TFLOPs: 63.78 | +[default7]: iteration 2922/ 3814 | consumed samples: 1496064 | consumed tokens: 3063939072 | elapsed time per iteration (s): 6.04 | learning rate: 8.096E-05 | global batch size: 512 | lm loss: 3.305381E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.765 | TFLOPs: 64.02 | +[default7]: iteration 2923/ 3814 | consumed samples: 1496576 | consumed tokens: 3064987648 | elapsed time per iteration (s): 6.01 | learning rate: 8.079E-05 | global batch size: 512 | lm loss: 3.312715E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.192 | TFLOPs: 64.35 | +[default7]: iteration 2924/ 3814 | consumed samples: 1497088 | consumed tokens: 3066036224 | elapsed time per iteration (s): 6.03 | learning rate: 8.062E-05 | global batch size: 512 | lm loss: 3.305657E+00 | loss scale: 131072.0 | grad norm: 0.128 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.863 | TFLOPs: 64.10 | +[default7]: iteration 2925/ 3814 | consumed samples: 1497600 | consumed tokens: 3067084800 | elapsed time per iteration (s): 5.91 | learning rate: 8.045E-05 | global batch size: 512 | lm loss: 3.288401E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.676 | TFLOPs: 65.47 | +[default7]: iteration 2926/ 3814 | consumed samples: 1498112 | consumed tokens: 3068133376 | elapsed time per iteration (s): 6.06 | learning rate: 8.028E-05 | global batch size: 512 | lm loss: 3.269238E+00 | loss scale: 131072.0 | grad norm: 0.125 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.485 | TFLOPs: 63.81 | +[default7]: iteration 2927/ 3814 | consumed samples: 1498624 | consumed tokens: 3069181952 | elapsed time per iteration (s): 5.86 | learning rate: 8.011E-05 | global batch size: 512 | lm loss: 3.311159E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 87.369 | TFLOPs: 65.99 | +[default7]: iteration 2928/ 3814 | consumed samples: 1499136 | consumed tokens: 3070230528 | elapsed time per iteration (s): 5.96 | learning rate: 7.994E-05 | global batch size: 512 | lm loss: 3.272950E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.923 | TFLOPs: 64.90 | +[default7]: iteration 2929/ 3814 | consumed samples: 1499648 | consumed tokens: 3071279104 | elapsed time per iteration (s): 5.97 | learning rate: 7.977E-05 | global batch size: 512 | lm loss: 3.304402E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.743 | TFLOPs: 64.76 | +[default7]: iteration 2930/ 3814 | consumed samples: 1500160 | consumed tokens: 3072327680 | elapsed time per iteration (s): 6.04 | learning rate: 7.960E-05 | global batch size: 512 | lm loss: 3.285833E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.799 | TFLOPs: 64.05 | +[default7]: iteration 2931/ 3814 | consumed samples: 1500672 | consumed tokens: 3073376256 | elapsed time per iteration (s): 6.01 | learning rate: 7.943E-05 | global batch size: 512 | lm loss: 3.273316E+00 | loss scale: 131072.0 | grad norm: 0.106 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.211 | TFLOPs: 64.36 | +[default7]: iteration 2932/ 3814 | consumed samples: 1501184 | consumed tokens: 3074424832 | elapsed time per iteration (s): 6.03 | learning rate: 7.926E-05 | global batch size: 512 | lm loss: 3.330441E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.871 | TFLOPs: 64.10 | +[default7]: iteration 2933/ 3814 | consumed samples: 1501696 | consumed tokens: 3075473408 | elapsed time per iteration (s): 6.04 | learning rate: 7.909E-05 | global batch size: 512 | lm loss: 3.274022E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.729 | TFLOPs: 64.00 | +[default7]: iteration 2934/ 3814 | consumed samples: 1502208 | consumed tokens: 3076521984 | elapsed time per iteration (s): 6.00 | learning rate: 7.892E-05 | global batch size: 512 | lm loss: 3.284838E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.330 | TFLOPs: 64.45 | +[default7]: iteration 2935/ 3814 | consumed samples: 1502720 | consumed tokens: 3077570560 | elapsed time per iteration (s): 5.94 | learning rate: 7.875E-05 | global batch size: 512 | lm loss: 3.316566E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.178 | TFLOPs: 65.09 | +[default7]: iteration 2936/ 3814 | consumed samples: 1503232 | consumed tokens: 3078619136 | elapsed time per iteration (s): 6.00 | learning rate: 7.858E-05 | global batch size: 512 | lm loss: 3.276876E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.325 | TFLOPs: 64.45 | +[default7]: iteration 2937/ 3814 | consumed samples: 1503744 | consumed tokens: 3079667712 | elapsed time per iteration (s): 6.05 | learning rate: 7.841E-05 | global batch size: 512 | lm loss: 3.263753E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.627 | TFLOPs: 63.92 | +[default7]: iteration 2938/ 3814 | consumed samples: 1504256 | consumed tokens: 3080716288 | elapsed time per iteration (s): 5.96 | learning rate: 7.824E-05 | global batch size: 512 | lm loss: 3.311192E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.895 | TFLOPs: 64.88 | +[default7]: iteration 2939/ 3814 | consumed samples: 1504768 | consumed tokens: 3081764864 | elapsed time per iteration (s): 5.95 | learning rate: 7.807E-05 | global batch size: 512 | lm loss: 3.314673E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.065 | TFLOPs: 65.01 | +[default7]: iteration 2940/ 3814 | consumed samples: 1505280 | consumed tokens: 3082813440 | elapsed time per iteration (s): 6.00 | learning rate: 7.790E-05 | global batch size: 512 | lm loss: 3.306876E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.325 | TFLOPs: 64.45 | +[default7]: iteration 2941/ 3814 | consumed samples: 1505792 | consumed tokens: 3083862016 | elapsed time per iteration (s): 5.99 | learning rate: 7.773E-05 | global batch size: 512 | lm loss: 3.269155E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.501 | TFLOPs: 64.58 | +[default7]: iteration 2942/ 3814 | consumed samples: 1506304 | consumed tokens: 3084910592 | elapsed time per iteration (s): 6.08 | learning rate: 7.757E-05 | global batch size: 512 | lm loss: 3.261297E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.181 | TFLOPs: 63.58 | +[default7]: iteration 2943/ 3814 | consumed samples: 1506816 | consumed tokens: 3085959168 | elapsed time per iteration (s): 6.19 | learning rate: 7.740E-05 | global batch size: 512 | lm loss: 3.322099E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 82.742 | TFLOPs: 62.50 | +[default7]: iteration 2944/ 3814 | consumed samples: 1507328 | consumed tokens: 3087007744 | elapsed time per iteration (s): 5.99 | learning rate: 7.723E-05 | global batch size: 512 | lm loss: 3.265065E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.437 | TFLOPs: 64.53 | +[default7]: iteration 2945/ 3814 | consumed samples: 1507840 | consumed tokens: 3088056320 | elapsed time per iteration (s): 6.00 | learning rate: 7.706E-05 | global batch size: 512 | lm loss: 3.292487E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.294 | TFLOPs: 64.42 | +[default7]: iteration 2946/ 3814 | consumed samples: 1508352 | consumed tokens: 3089104896 | elapsed time per iteration (s): 6.04 | learning rate: 7.689E-05 | global batch size: 512 | lm loss: 3.274602E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.790 | TFLOPs: 64.04 | +[default7]: iteration 2947/ 3814 | consumed samples: 1508864 | consumed tokens: 3090153472 | elapsed time per iteration (s): 6.00 | learning rate: 7.673E-05 | global batch size: 512 | lm loss: 3.291869E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.365 | TFLOPs: 64.48 | +[default7]: iteration 2948/ 3814 | consumed samples: 1509376 | consumed tokens: 3091202048 | elapsed time per iteration (s): 6.02 | learning rate: 7.656E-05 | global batch size: 512 | lm loss: 3.324450E+00 | loss scale: 131072.0 | grad norm: 0.119 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.105 | TFLOPs: 64.28 | +[default7]: iteration 2949/ 3814 | consumed samples: 1509888 | consumed tokens: 3092250624 | elapsed time per iteration (s): 6.00 | learning rate: 7.639E-05 | global batch size: 512 | lm loss: 3.280611E+00 | loss scale: 131072.0 | grad norm: 0.120 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.287 | TFLOPs: 64.42 | +[default7]: iteration 2950/ 3814 | consumed samples: 1510400 | consumed tokens: 3093299200 | elapsed time per iteration (s): 6.01 | learning rate: 7.622E-05 | global batch size: 512 | lm loss: 3.303330E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.189 | TFLOPs: 64.34 | +[default7]: iteration 2951/ 3814 | consumed samples: 1510912 | consumed tokens: 3094347776 | elapsed time per iteration (s): 5.96 | learning rate: 7.606E-05 | global batch size: 512 | lm loss: 3.300446E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.886 | TFLOPs: 64.87 | +[default7]: iteration 2952/ 3814 | consumed samples: 1511424 | consumed tokens: 3095396352 | elapsed time per iteration (s): 5.95 | learning rate: 7.589E-05 | global batch size: 512 | lm loss: 3.305744E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.080 | TFLOPs: 65.02 | +[default7]: iteration 2953/ 3814 | consumed samples: 1511936 | consumed tokens: 3096444928 | elapsed time per iteration (s): 6.00 | learning rate: 7.572E-05 | global batch size: 512 | lm loss: 3.336224E+00 | loss scale: 131072.0 | grad norm: 0.113 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.386 | TFLOPs: 64.49 | +[default7]: iteration 2954/ 3814 | consumed samples: 1512448 | consumed tokens: 3097493504 | elapsed time per iteration (s): 6.02 | learning rate: 7.556E-05 | global batch size: 512 | lm loss: 3.290812E+00 | loss scale: 131072.0 | grad norm: 0.123 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.061 | TFLOPs: 64.25 | +[default7]: iteration 2955/ 3814 | consumed samples: 1512960 | consumed tokens: 3098542080 | elapsed time per iteration (s): 6.02 | learning rate: 7.539E-05 | global batch size: 512 | lm loss: 3.317093E+00 | loss scale: 131072.0 | grad norm: 0.118 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.000 | TFLOPs: 64.20 | +[default7]: iteration 2956/ 3814 | consumed samples: 1513472 | consumed tokens: 3099590656 | elapsed time per iteration (s): 6.00 | learning rate: 7.522E-05 | global batch size: 512 | lm loss: 3.284427E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.401 | TFLOPs: 64.50 | +[default7]: iteration 2957/ 3814 | consumed samples: 1513984 | consumed tokens: 3100639232 | elapsed time per iteration (s): 6.01 | learning rate: 7.506E-05 | global batch size: 512 | lm loss: 3.271463E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.219 | TFLOPs: 64.37 | +[default7]: iteration 2958/ 3814 | consumed samples: 1514496 | consumed tokens: 3101687808 | elapsed time per iteration (s): 6.10 | learning rate: 7.489E-05 | global batch size: 512 | lm loss: 3.281418E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.959 | TFLOPs: 63.42 | +[default7]: iteration 2959/ 3814 | consumed samples: 1515008 | consumed tokens: 3102736384 | elapsed time per iteration (s): 5.98 | learning rate: 7.473E-05 | global batch size: 512 | lm loss: 3.297164E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.572 | TFLOPs: 64.63 | +[default7]: iteration 2960/ 3814 | consumed samples: 1515520 | consumed tokens: 3103784960 | elapsed time per iteration (s): 6.04 | learning rate: 7.456E-05 | global batch size: 512 | lm loss: 3.301431E+00 | loss scale: 131072.0 | grad norm: 0.122 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.766 | TFLOPs: 64.02 | +[default7]: iteration 2961/ 3814 | consumed samples: 1516032 | consumed tokens: 3104833536 | elapsed time per iteration (s): 6.02 | learning rate: 7.439E-05 | global batch size: 512 | lm loss: 3.253586E+00 | loss scale: 131072.0 | grad norm: 0.111 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.020 | TFLOPs: 64.22 | +[default7]: iteration 2962/ 3814 | consumed samples: 1516544 | consumed tokens: 3105882112 | elapsed time per iteration (s): 6.00 | learning rate: 7.423E-05 | global batch size: 512 | lm loss: 3.296091E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.267 | TFLOPs: 64.40 | +[default7]: iteration 2963/ 3814 | consumed samples: 1517056 | consumed tokens: 3106930688 | elapsed time per iteration (s): 6.02 | learning rate: 7.406E-05 | global batch size: 512 | lm loss: 3.295166E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.107 | TFLOPs: 64.28 | +[default7]: iteration 2964/ 3814 | consumed samples: 1517568 | consumed tokens: 3107979264 | elapsed time per iteration (s): 5.93 | learning rate: 7.390E-05 | global batch size: 512 | lm loss: 3.316705E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.383 | TFLOPs: 65.25 | +[default7]: iteration 2965/ 3814 | consumed samples: 1518080 | consumed tokens: 3109027840 | elapsed time per iteration (s): 5.92 | learning rate: 7.373E-05 | global batch size: 512 | lm loss: 3.293276E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.549 | TFLOPs: 65.37 | +[default7]: iteration 2966/ 3814 | consumed samples: 1518592 | consumed tokens: 3110076416 | elapsed time per iteration (s): 6.03 | learning rate: 7.357E-05 | global batch size: 512 | lm loss: 3.320440E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 84.843 | TFLOPs: 64.08 | +[default7]: iteration 2967/ 3814 | consumed samples: 1519104 | consumed tokens: 3111124992 | elapsed time per iteration (s): 5.93 | learning rate: 7.340E-05 | global batch size: 512 | lm loss: 3.308064E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.313 | TFLOPs: 65.19 | +[default7]: iteration 2968/ 3814 | consumed samples: 1519616 | consumed tokens: 3112173568 | elapsed time per iteration (s): 5.97 | learning rate: 7.324E-05 | global batch size: 512 | lm loss: 3.305236E+00 | loss scale: 131072.0 | grad norm: 0.121 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.717 | TFLOPs: 64.74 | +[default7]: iteration 2969/ 3814 | consumed samples: 1520128 | consumed tokens: 3113222144 | elapsed time per iteration (s): 5.99 | learning rate: 7.308E-05 | global batch size: 512 | lm loss: 3.295858E+00 | loss scale: 131072.0 | grad norm: 0.116 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.407 | TFLOPs: 64.51 | +[default7]: iteration 2970/ 3814 | consumed samples: 1520640 | consumed tokens: 3114270720 | elapsed time per iteration (s): 5.99 | learning rate: 7.291E-05 | global batch size: 512 | lm loss: 3.264472E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.458 | TFLOPs: 64.55 | +[default7]: iteration 2971/ 3814 | consumed samples: 1521152 | consumed tokens: 3115319296 | elapsed time per iteration (s): 5.90 | learning rate: 7.275E-05 | global batch size: 512 | lm loss: 3.301223E+00 | loss scale: 131072.0 | grad norm: 0.114 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 86.725 | TFLOPs: 65.50 | +[default7]: iteration 2972/ 3814 | consumed samples: 1521664 | consumed tokens: 3116367872 | elapsed time per iteration (s): 6.12 | learning rate: 7.258E-05 | global batch size: 512 | lm loss: 3.281977E+00 | loss scale: 131072.0 | grad norm: 0.109 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.659 | TFLOPs: 63.19 | +[default7]: iteration 2973/ 3814 | consumed samples: 1522176 | consumed tokens: 3117416448 | elapsed time per iteration (s): 6.12 | learning rate: 7.242E-05 | global batch size: 512 | lm loss: 3.280967E+00 | loss scale: 131072.0 | grad norm: 0.115 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.626 | TFLOPs: 63.16 | +[default7]: iteration 2974/ 3814 | consumed samples: 1522688 | consumed tokens: 3118465024 | elapsed time per iteration (s): 5.99 | learning rate: 7.226E-05 | global batch size: 512 | lm loss: 3.294157E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.506 | TFLOPs: 64.58 | +[default7]: iteration 2975/ 3814 | consumed samples: 1523200 | consumed tokens: 3119513600 | elapsed time per iteration (s): 5.99 | learning rate: 7.209E-05 | global batch size: 512 | lm loss: 3.286695E+00 | loss scale: 131072.0 | grad norm: 0.117 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.523 | TFLOPs: 64.60 | +[default7]: iteration 2976/ 3814 | consumed samples: 1523712 | consumed tokens: 3120562176 | elapsed time per iteration (s): 6.01 | learning rate: 7.193E-05 | global batch size: 512 | lm loss: 3.309640E+00 | loss scale: 131072.0 | grad norm: 0.112 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 85.166 | TFLOPs: 64.33 | +[default7]: iteration 2977/ 3814 | consumed samples: 1524224 | consumed tokens: 3121610752 | elapsed time per iteration (s): 6.14 | learning rate: 7.177E-05 | global batch size: 512 | lm loss: 3.277428E+00 | loss scale: 131072.0 | grad norm: 0.110 | num zeros: 0.0 | number of skipped iterations: 0 | number of nan iterations: 0 | samples per second: 83.355 | TFLOPs: 62.96 | +slurmstepd: error: *** STEP 1219019.0 ON jean-zay-iam01 CANCELLED AT 2023-02-16T12:31:27 DUE TO TIME LIMIT *** +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195819 closing signal SIGTERM +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435512 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040902 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040903 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435513 closing signal SIGTERM +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777959 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040904 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195820 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435514 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040905 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777960 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195821 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040906 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040907 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195822 closing signal SIGTERM +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777961 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186752 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040908 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195823 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435515 closing signal SIGTERM +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040909 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195824 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925184 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195825 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435516 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777962 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195826 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435517 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186753 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925185 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777963 closing signal SIGTERM +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925186 closing signal SIGTERM +srun: Job step aborted: Waiting up to 62 seconds for job step to finish. +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435518 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801826 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186754 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777964 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801827 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925187 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435519 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777965 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925188 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777966 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801828 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186755 closing signal SIGTERM +WARNING:torch.distributed.elastic.agent.server.api:Received 15 death signal, shutting down workers +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925189 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919382 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186756 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919383 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925190 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919384 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801829 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919385 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801830 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186757 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919386 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801831 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919387 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925191 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801832 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919388 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919389 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186758 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801833 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186759 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040902 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040903 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040904 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040905 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040906 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040907 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040908 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 4040909 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435512 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435513 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435514 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435515 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435516 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435517 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435518 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 435519 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777959 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777960 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777961 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777962 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777963 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777964 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777965 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 777966 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186752 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186753 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186754 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186755 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186756 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186757 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186758 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 186759 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801826 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801827 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801828 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801829 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801830 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801831 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801832 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2801833 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925184 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925185 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925186 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925187 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925188 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925189 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925190 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 1925191 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195819 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195820 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195821 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195822 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195823 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195824 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195825 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 195826 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919382 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919383 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919384 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919385 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919386 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919387 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919388 closing signal SIGTERM +WARNING:torch.distributed.elastic.multiprocessing.api:Sending process 2919389 closing signal SIGTERM