Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

logs.txt

@@ -0,0 +1,324 @@
+[2024-08-21 07:39:35,347] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+FLYWHEEL_USE_CUDA_DEVICES = 0,1,2,3,4,5,6,7
+CUDA_VISIBLE_DEVICES = 0,1,2,3,4,5,6,7
+local_rank = 5, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 5
+Rank = 5
+[2024-08-21 07:39:45,571] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+local_rank = 1, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 1
+Rank = 1
+[2024-08-21 07:39:45,640] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+local_rank = 0, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 0
+Rank = 0
+[2024-08-21 07:39:45,918] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+local_rank = 2, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 2
+Rank = 2
+[2024-08-21 07:39:45,955] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+local_rank = 3, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 3
+Rank = 3
+[2024-08-21 07:39:46,251] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+local_rank = 6, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 6
+local_rank = 4, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 4
+Rank = 6
+Rank = 4
+[2024-08-21 07:39:46,291] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+[2024-08-21 07:39:46,293] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+local_rank = 7, device_ranks = ['0', '1', '2', '3', '4', '5', '6', '7'], set device_rank = 7
+Rank = 7
+[2024-08-21 07:39:46,306] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  async_io: please install the libaio-dev package with apt [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found. [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.
+
+ninja: no work to do.
+Time to load cpu_adam op: 0.35883283615112305 seconds
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+ninja: no work to do.
+Time to load cpu_adam op: 0.3585677146911621 seconds
+[2024-08-21 07:39:47,345] [INFO] [comm.py:637:init_distributed] cdb=None
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+[2024-08-21 07:39:47,547] [INFO] [comm.py:637:init_distributed] cdb=None
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+ninja: no work to do.
+Time to load cpu_adam op: 0.34619593620300293 seconds
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+Installed CUDA version 12.5 does not match the version torch was compiled with 12.4 but since the APIs are compatible, accepting this combination
+ninja: no work to do.
+Time to load cpu_adam op: 0.30925703048706055 seconds
+Time to load cpu_adam op: 0.3485276699066162 seconds
+Time to load cpu_adam op: 0.3466987609863281 seconds
+Time to load cpu_adam op: 0.362682580947876 seconds
+Time to load cpu_adam op: 0.4855527877807617 seconds
+[2024-08-21 07:39:47,967] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-08-21 07:39:48,159] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-08-21 07:39:48,159] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-08-21 07:39:48,160] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-08-21 07:39:48,160] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-08-21 07:39:48,161] [INFO] [comm.py:637:init_distributed] cdb=None
+[2024-08-21 07:40:02,482] [INFO] [partition_parameters.py:345:__exit__] finished initializing model - num_params = 363, num_elems = 13.02B
+Is prompt masked: True
+Is prompt masked: True
+Is prompt masked: True
+Is prompt masked: True
+Is prompt masked: True
+Is prompt masked: True
+Is prompt masked: True
+Is prompt masked: True
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+[2024-08-21 07:40:10,409] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed info: version=0.14.5, git-hash=unknown, git-branch=unknown
+[2024-08-21 07:40:10,420] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Flops Profiler Enabled: False
+[2024-08-21 07:40:10,421] [INFO] [logging.py:96:log_dist] [Rank 0] Using client Optimizer as basic optimizer
+[2024-08-21 07:40:10,421] [INFO] [logging.py:96:log_dist] [Rank 0] Removing param_group that has no 'params' in the basic Optimizer
+[2024-08-21 07:40:10,432] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Basic Optimizer = DeepSpeedCPUAdam
+[2024-08-21 07:40:10,432] [INFO] [utils.py:59:is_zero_supported_optimizer] Checking ZeRO support for optimizer=DeepSpeedCPUAdam type=<class 'deepspeed.ops.adam.cpu_adam.DeepSpeedCPUAdam'>
+[2024-08-21 07:40:10,433] [INFO] [logging.py:96:log_dist] [Rank 0] Creating fp16 ZeRO stage 3 optimizer, MiCS is enabled False, Hierarchical params gather False
+[2024-08-21 07:40:10,433] [INFO] [logging.py:96:log_dist] [Rank 0] Creating torch.bfloat16 ZeRO stage 3 optimizer
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+Adam Optimizer #0 is created with AVX512 arithmetic capability.
+Config: alpha=0.000020, betas=(0.900000, 0.999000), weight_decay=0.010000, adam_w=1
+[2024-08-21 07:40:10,621] [INFO] [utils.py:781:see_memory_usage] Stage 3 initialize beginning
+[2024-08-21 07:40:10,622] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.61 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:10,622] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 66.66 GB, percent = 3.6%
+[2024-08-21 07:40:10,623] [INFO] [stage3.py:130:__init__] Reduce bucket size 26214400
+[2024-08-21 07:40:10,623] [INFO] [stage3.py:131:__init__] Prefetch bucket size 23592960
+[2024-08-21 07:40:10,728] [INFO] [utils.py:781:see_memory_usage] DeepSpeedZeRoOffload initialize [begin]
+[2024-08-21 07:40:10,729] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:10,729] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 66.66 GB, percent = 3.6%
+Parameter Offload: Total persistent parameters: 414720 in 81 params
+[2024-08-21 07:40:10,847] [INFO] [utils.py:781:see_memory_usage] DeepSpeedZeRoOffload initialize [end]
+[2024-08-21 07:40:10,848] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:10,848] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 66.66 GB, percent = 3.6%
+[2024-08-21 07:40:10,952] [INFO] [utils.py:781:see_memory_usage] Before creating fp16 partitions
+[2024-08-21 07:40:10,953] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:10,953] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 66.66 GB, percent = 3.6%
+[2024-08-21 07:40:14,047] [INFO] [utils.py:781:see_memory_usage] After creating fp16 partitions: 2
+[2024-08-21 07:40:14,048] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:14,048] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 106.86 GB, percent = 5.7%
+[2024-08-21 07:40:14,291] [INFO] [utils.py:781:see_memory_usage] Before creating fp32 partitions
+[2024-08-21 07:40:14,291] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:14,291] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 112.53 GB, percent = 6.0%
+[2024-08-21 07:40:17,107] [INFO] [utils.py:781:see_memory_usage] After creating fp32 partitions
+[2024-08-21 07:40:17,108] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:17,108] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 147.97 GB, percent = 7.9%
+[2024-08-21 07:40:17,286] [INFO] [utils.py:781:see_memory_usage] Before initializing optimizer states
+[2024-08-21 07:40:17,286] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:17,286] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 154.04 GB, percent = 8.2%
+[2024-08-21 07:40:23,940] [INFO] [utils.py:781:see_memory_usage] After initializing optimizer states
+[2024-08-21 07:40:23,940] [INFO] [utils.py:782:see_memory_usage] MA 0.0 GB         Max_MA 0.0 GB         CA 0.62 GB         Max_CA 1 GB 
+[2024-08-21 07:40:23,941] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 213.22 GB, percent = 11.4%
+[2024-08-21 07:40:23,941] [INFO] [stage3.py:485:_setup_for_real_optimizer] optimizer state initialized
+[2024-08-21 07:40:27,272] [INFO] [utils.py:781:see_memory_usage] After initializing ZeRO optimizer
+[2024-08-21 07:40:27,273] [INFO] [utils.py:782:see_memory_usage] MA 0.05 GB         Max_MA 0.66 GB         CA 0.92 GB         Max_CA 1 GB 
+[2024-08-21 07:40:27,273] [INFO] [utils.py:789:see_memory_usage] CPU Virtual Memory:  used = 245.98 GB, percent = 13.2%
+[2024-08-21 07:40:27,273] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed Final Optimizer = DeepSpeedZeroOptimizer_Stage3
+[2024-08-21 07:40:27,273] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed using configured LR scheduler = None
+[2024-08-21 07:40:27,273] [INFO] [logging.py:96:log_dist] [Rank 0] DeepSpeed LR Scheduler = None
+[2024-08-21 07:40:27,273] [INFO] [logging.py:96:log_dist] [Rank 0] step=0, skipped=0, lr=[0.0], mom=[(0.9, 0.999)]
+[2024-08-21 07:40:27,274] [INFO] [config.py:997:print] DeepSpeedEngine configuration:
+[2024-08-21 07:40:27,274] [INFO] [config.py:1001:print]   activation_checkpointing_config  {
+    "partition_activations": false, 
+    "contiguous_memory_optimization": false, 
+    "cpu_checkpointing": false, 
+    "number_checkpoints": null, 
+    "synchronize_checkpoint_boundary": false, 
+    "profile": false
+}
+[2024-08-21 07:40:27,274] [INFO] [config.py:1001:print]   aio_config ................... {'block_size': 1048576, 'queue_depth': 8, 'thread_count': 1, 'single_submit': False, 'overlap_events': True}
+[2024-08-21 07:40:27,274] [INFO] [config.py:1001:print]   amp_enabled .................. False
+[2024-08-21 07:40:27,274] [INFO] [config.py:1001:print]   amp_params ................... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   autotuning_config ............ {
+    "enabled": false, 
+    "start_step": null, 
+    "end_step": null, 
+    "metric_path": null, 
+    "arg_mappings": null, 
+    "metric": "throughput", 
+    "model_info": null, 
+    "results_dir": "autotuning_results", 
+    "exps_dir": "autotuning_exps", 
+    "overwrite": true, 
+    "fast": true, 
+    "start_profile_step": 3, 
+    "end_profile_step": 5, 
+    "tuner_type": "gridsearch", 
+    "tuner_early_stopping": 5, 
+    "tuner_num_trials": 50, 
+    "model_info_path": null, 
+    "mp_size": 1, 
+    "max_train_batch_size": null, 
+    "min_train_batch_size": 1, 
+    "max_train_micro_batch_size_per_gpu": 1.024000e+03, 
+    "min_train_micro_batch_size_per_gpu": 1, 
+    "num_tuning_micro_batch_sizes": 3
+}
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   bfloat16_enabled ............. True
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   bfloat16_immediate_grad_update  False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   checkpoint_parallel_write_pipeline  False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   checkpoint_tag_validation_enabled  True
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   checkpoint_tag_validation_fail  False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   comms_config ................. <deepspeed.comm.config.DeepSpeedCommsConfig object at 0x7f97060b8dd0>
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   communication_data_type ...... None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001: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}}
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   curriculum_enabled_legacy .... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   curriculum_params_legacy ..... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   data_efficiency_config ....... {'enabled': False, 'seed': 1234, 'data_sampling': {'enabled': False, 'num_epochs': 1000, 'num_workers': 0, 'curriculum_learning': {'enabled': False}}, 'data_routing': {'enabled': False, 'random_ltd': {'enabled': False, 'layer_token_lr_schedule': {'enabled': False}}}}
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   data_efficiency_enabled ...... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   dataloader_drop_last ......... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   disable_allgather ............ False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   dump_state ................... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   dynamic_loss_scale_args ...... None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_enabled ........... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_gas_boundary_resolution  1
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_layer_name ........ bert.encoder.layer
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_layer_num ......... 0
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_max_iter .......... 100
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_stability ......... 1e-06
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_tol ............... 0.01
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   eigenvalue_verbose ........... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   elasticity_enabled ........... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   flops_profiler_config ........ {
+    "enabled": false, 
+    "recompute_fwd_factor": 0.0, 
+    "profile_step": 1, 
+    "module_depth": -1, 
+    "top_modules": 1, 
+    "detailed": true, 
+    "output_file": null
+}
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   fp16_auto_cast ............... None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   fp16_enabled ................. False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   fp16_master_weights_and_gradients  False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   global_rank .................. 0
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   grad_accum_dtype ............. None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   gradient_accumulation_steps .. 1
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   gradient_clipping ............ 1.0
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   gradient_predivide_factor .... 1.0
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   graph_harvesting ............. False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   hybrid_engine ................ enabled=False max_out_tokens=512 inference_tp_size=1 release_inference_cache=False pin_parameters=True tp_gather_partition_size=8
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   initial_dynamic_scale ........ 1
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   load_universal_checkpoint .... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   loss_scale ................... 1.0
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   memory_breakdown ............. False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   mics_hierarchial_params_gather  False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   mics_shard_size .............. -1
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   monitor_config ............... tensorboard=TensorBoardConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') comet=CometConfig(enabled=False, samples_log_interval=100, project=None, workspace=None, api_key=None, experiment_name=None, experiment_key=None, online=None, mode=None) wandb=WandbConfig(enabled=False, group=None, team=None, project='deepspeed') csv_monitor=CSVConfig(enabled=False, output_path='', job_name='DeepSpeedJobName') enabled=False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   nebula_config ................ {
+    "enabled": false, 
+    "persistent_storage_path": null, 
+    "persistent_time_interval": 100, 
+    "num_of_version_in_retention": 2, 
+    "enable_nebula_load": true, 
+    "load_path": null
+}
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   optimizer_legacy_fusion ...... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   optimizer_name ............... None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   optimizer_params ............. None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   pipeline ..................... {'stages': 'auto', 'partition': 'best', 'seed_layers': False, 'activation_checkpoint_interval': 0, 'pipe_partitioned': True, 'grad_partitioned': True}
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   pld_enabled .................. False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   pld_params ................... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   prescale_gradients ........... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   scheduler_name ............... None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   scheduler_params ............. None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   seq_parallel_communication_data_type  torch.float32
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   sparse_attention ............. None
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   sparse_gradients_enabled ..... False
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   steps_per_print .............. inf
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   timers_config ................ enabled=True synchronized=True
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   train_batch_size ............. 128
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   train_micro_batch_size_per_gpu  16
+[2024-08-21 07:40:27,275] [INFO] [config.py:1001:print]   use_data_before_expert_parallel_  False
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   use_node_local_storage ....... False
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   wall_clock_breakdown ......... False
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   weight_quantization_config ... None
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   world_size ................... 8
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   zero_allow_untested_optimizer  True
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   zero_config .................. stage=3 contiguous_gradients=True reduce_scatter=True reduce_bucket_size=26214400 use_multi_rank_bucket_allreduce=True allgather_partitions=True allgather_bucket_size=500,000,000 overlap_comm=True load_from_fp32_weights=True elastic_checkpoint=False offload_param=DeepSpeedZeroOffloadParamConfig(device='cpu', nvme_path=None, buffer_count=5, buffer_size=100,000,000, max_in_cpu=1,000,000,000, pin_memory=True) offload_optimizer=DeepSpeedZeroOffloadOptimizerConfig(device='cpu', nvme_path=None, buffer_count=4, pin_memory=True, pipeline=False, pipeline_read=False, pipeline_write=False, fast_init=False, ratio=1.0) sub_group_size=1000000000 cpu_offload_param=None cpu_offload_use_pin_memory=None cpu_offload=None prefetch_bucket_size=23592960 param_persistence_threshold=51200 model_persistence_threshold=sys.maxsize max_live_parameters=6000000000 max_reuse_distance=6000000000 gather_16bit_weights_on_model_save=False use_all_reduce_for_fetch_params=False stage3_gather_fp16_weights_on_model_save=False ignore_unused_parameters=True legacy_stage1=False round_robin_gradients=False zero_hpz_partition_size=1 zero_quantized_weights=False zero_quantized_nontrainable_weights=False zero_quantized_gradients=False mics_shard_size=-1 mics_hierarchical_params_gather=False memory_efficient_linear=True pipeline_loading_checkpoint=False override_module_apply=True
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   zero_enabled ................. True
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   zero_force_ds_cpu_optimizer .. True
+[2024-08-21 07:40:27,276] [INFO] [config.py:1001:print]   zero_optimization_stage ...... 3
+[2024-08-21 07:40:27,276] [INFO] [config.py:987:print_user_config]   json = {
+    "bf16": {
+        "enabled": true
+    }, 
+    "zero_optimization": {
+        "stage": 3, 
+        "offload_optimizer": {
+            "device": "cpu", 
+            "pin_memory": true
+        }, 
+        "offload_param": {
+            "device": "cpu", 
+            "pin_memory": true
+        }, 
+        "overlap_comm": true, 
+        "contiguous_gradients": true, 
+        "sub_group_size": 1.000000e+09, 
+        "reduce_bucket_size": 2.621440e+07, 
+        "stage3_prefetch_bucket_size": 2.359296e+07, 
+        "stage3_param_persistence_threshold": 5.120000e+04, 
+        "stage3_max_live_parameters": 6.000000e+09, 
+        "stage3_max_reuse_distance": 6.000000e+09, 
+        "stage3_gather_16bit_weights_on_model_save": false
+    }, 
+    "gradient_accumulation_steps": 1, 
+    "gradient_clipping": 1.0, 
+    "steps_per_print": inf, 
+    "train_batch_size": 128, 
+    "train_micro_batch_size_per_gpu": 16, 
+    "wall_clock_breakdown": false, 
+    "fp16": {
+        "enabled": false
+    }, 
+    "zero_allow_untested_optimizer": true
+}
+ [WARNING]  async_io requires the dev libaio .so object and headers but these were not found.
+ [WARNING]  async_io: please install the libaio-dev package with apt
+ [WARNING]  If libaio is already installed (perhaps from source), try setting the CFLAGS and LDFLAGS environment variables to where it can be found.

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,84 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}