End of training

20250513_005845.log

@@ -0,0 +1,178 @@
+[2025-05-13 01:06:13] Created output directory: train_results/roberta-large_ds100_upsample1000
+[2025-05-13 01:06:13] Chat mode disabled
+[2025-05-13 01:06:13] Model size is 3B or smaller (0 B). Using full fine-tuning.
+[2025-05-13 01:06:13] Adjusted parameters for roberta model:
+[2025-05-13 01:06:13]   - LEARNING_RATE: 1e-5
+[2025-05-13 01:06:13]   - BATCH_SIZE: 512
+[2025-05-13 01:06:13]   - GRADIENT_ACCUMULATION_STEPS: 1
+[2025-05-13 01:06:13] No QA format data will be used
+[2025-05-13 01:06:13] Limiting dataset size to: 100 samples
+[2025-05-13 01:06:13] =======================================
+[2025-05-13 01:06:13] Starting training for model: roberta-large
+[2025-05-13 01:06:13] =======================================
+[2025-05-13 01:06:13] CUDA_VISIBLE_DEVICES: 0,1
+[2025-05-13 01:06:13] WANDB_PROJECT: wikidyk-ar
+[2025-05-13 01:06:13] DATA_PATH: data/wikidyk2022-2025_01082025_gpt-4o_evalv2_pages_formatted_combined_v2.json
+[2025-05-13 01:06:13] Global Batch Size: 1024
+[2025-05-13 01:06:13] Data Size: 100
+[2025-05-13 01:06:13] Executing command: torchrun --nproc_per_node "2" --master-port 29501 src/train.py       --model_name_or_path "roberta-large"       --data_path "data/wikidyk2022-2025_01082025_gpt-4o_evalv2_pages_formatted_combined_v2.json"       --output_dir "train_results/roberta-large_ds100_upsample1000"       --num_upsample "1000"       --per_device_train_batch_size "512"       --gradient_accumulation_steps "1"       --learning_rate "1e-5"       --num_train_epochs "1"       --model_max_length "32768"       --report_to wandb --logging_steps 50 --save_strategy no       --bf16 True --use_flash_attention_2 True       --qa_data_ratio "-1"       --predict_mask "false"                            --ds_size 100
+[2025-05-13 01:06:13] Training started at Tue May 13 01:06:13 UTC 2025
+W0513 01:06:14.468000 443076 site-packages/torch/distributed/run.py:792] 
+W0513 01:06:14.468000 443076 site-packages/torch/distributed/run.py:792] *****************************************
+W0513 01:06:14.468000 443076 site-packages/torch/distributed/run.py:792] 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. 
+W0513 01:06:14.468000 443076 site-packages/torch/distributed/run.py:792] *****************************************
+WARNING:root:Output directory: train_results/roberta-large_ds100_upsample1000
+WARNING:root:Output directory: train_results/roberta-large_ds100_upsample1000
+WARNING:root:Loading data...
+WARNING:root:Loading data...
+WARNING:root:Dataset initialized with all QA data:
+WARNING:root:  - 0 QA examples
+WARNING:root:  - 100 fact examples with upsampling factor 1000
+WARNING:root:  - Total examples: 100000
+/root/yuwei/WikiDYKEvalV2/src/train.py:119: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
+  trainer = Trainer(model=model, tokenizer=tokenizer, args=training_args, **data_module)
+WARNING:root:Dataset initialized with all QA data:
+WARNING:root:  - 0 QA examples
+WARNING:root:  - 100 fact examples with upsampling factor 1000
+WARNING:root:  - Total examples: 100000
+/root/yuwei/WikiDYKEvalV2/src/train.py:119: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
+  trainer = Trainer(model=model, tokenizer=tokenizer, args=training_args, **data_module)
+wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
+wandb: Currently logged in as: yuweiz to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
+wandb: Tracking run with wandb version 0.19.11
+wandb: Run data is saved locally in /root/yuwei/WikiDYKEvalV2/wandb/run-20250513_010628-sr78j4sb
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run train_results/roberta-large_ds100_upsample1000
+wandb: ⭐️ View project at https://wandb.ai/yuweiz/wikidyk-ar
+wandb: 🚀 View run at https://wandb.ai/yuweiz/wikidyk-ar/runs/sr78j4sb
+
  0%|          | 0/98 [00:00<?, ?it/s][rank1]:[W513 01:06:31.932999163 reducer.cpp:1400] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
+Traceback (most recent call last):
+  File "/root/yuwei/WikiDYKEvalV2/src/train.py", line 134, in <module>
+    train()
+  File "/root/yuwei/WikiDYKEvalV2/src/train.py", line 122, in train
+    trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 2245, in train
+    return inner_training_loop(
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 2560, in _inner_training_loop
+    tr_loss_step = self.training_step(model, inputs, num_items_in_batch)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 3736, in training_step
+    loss = self.compute_loss(model, inputs, num_items_in_batch=num_items_in_batch)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 3801, in compute_loss
+    outputs = model(**inputs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1643, in forward
+    else self._run_ddp_forward(*inputs, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1459, in _run_ddp_forward
+    return self.module(*inputs, **kwargs)  # type: ignore[index]
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
+    return self._call_impl(*args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
+    return forward_call(*args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 814, in forward
+    return model_forward(*args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 802, in __call__
+    return convert_to_fp32(self.model_forward(*args, **kwargs))
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 781, in convert_to_fp32
+    return recursively_apply(_convert_to_fp32, tensor, test_type=_is_fp16_bf16_tensor)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 118, in recursively_apply
+    {
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 119, in <dictcomp>
+    k: recursively_apply(
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 126, in recursively_apply
+    return func(data, *args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 773, in _convert_to_fp32
+    return tensor.float()
+torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.03 GiB. GPU 0 has a total capacity of 79.25 GiB of which 3.84 GiB is free. Process 2436654 has 41.89 GiB memory in use. Process 2487807 has 33.51 GiB memory in use. Of the allocated memory 32.49 GiB is allocated by PyTorch, and 198.04 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
+[rank0]: Traceback (most recent call last):
+[rank0]:   File "/root/yuwei/WikiDYKEvalV2/src/train.py", line 134, in <module>
+[rank0]:     train()
+[rank0]:   File "/root/yuwei/WikiDYKEvalV2/src/train.py", line 122, in train
+[rank0]:     trainer.train(resume_from_checkpoint=training_args.resume_from_checkpoint)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 2245, in train
+[rank0]:     return inner_training_loop(
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 2560, in _inner_training_loop
+[rank0]:     tr_loss_step = self.training_step(model, inputs, num_items_in_batch)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 3736, in training_step
+[rank0]:     loss = self.compute_loss(model, inputs, num_items_in_batch=num_items_in_batch)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/transformers/trainer.py", line 3801, in compute_loss
+[rank0]:     outputs = model(**inputs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1643, in forward
+[rank0]:     else self._run_ddp_forward(*inputs, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/parallel/distributed.py", line 1459, in _run_ddp_forward
+[rank0]:     return self.module(*inputs, **kwargs)  # type: ignore[index]
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1739, in _wrapped_call_impl
+[rank0]:     return self._call_impl(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1750, in _call_impl
+[rank0]:     return forward_call(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 814, in forward
+[rank0]:     return model_forward(*args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 802, in __call__
+[rank0]:     return convert_to_fp32(self.model_forward(*args, **kwargs))
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 781, in convert_to_fp32
+[rank0]:     return recursively_apply(_convert_to_fp32, tensor, test_type=_is_fp16_bf16_tensor)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 118, in recursively_apply
+[rank0]:     {
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 119, in <dictcomp>
+[rank0]:     k: recursively_apply(
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 126, in recursively_apply
+[rank0]:     return func(data, *args, **kwargs)
+[rank0]:   File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/accelerate/utils/operations.py", line 773, in _convert_to_fp32
+[rank0]:     return tensor.float()
+[rank0]: torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 4.03 GiB. GPU 0 has a total capacity of 79.25 GiB of which 3.84 GiB is free. Process 2436654 has 41.89 GiB memory in use. Process 2487807 has 33.51 GiB memory in use. Of the allocated memory 32.49 GiB is allocated by PyTorch, and 198.04 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation.  See documentation for Memory Management  (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)
+wandb: 
+wandb: 🚀 View run train_results/roberta-large_ds100_upsample1000 at: https://wandb.ai/yuweiz/wikidyk-ar/runs/sr78j4sb
+wandb: Find logs at: wandb/run-20250513_010628-sr78j4sb/logs
+W0513 01:06:34.206000 443076 site-packages/torch/distributed/elastic/multiprocessing/api.py:897] Sending process 443142 closing signal SIGTERM
+E0513 01:06:34.521000 443076 site-packages/torch/distributed/elastic/multiprocessing/api.py:869] failed (exitcode: 1) local_rank: 0 (pid: 443141) of binary: /root/miniconda3/envs/wikidyk/bin/python
+Traceback (most recent call last):
+  File "/root/miniconda3/envs/wikidyk/bin/torchrun", line 8, in <module>
+    sys.exit(main())
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/distributed/elastic/multiprocessing/errors/__init__.py", line 355, in wrapper
+    return f(*args, **kwargs)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/distributed/run.py", line 918, in main
+    run(args)
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/distributed/run.py", line 909, in run
+    elastic_launch(
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 138, in __call__
+    return launch_agent(self._config, self._entrypoint, list(args))
+  File "/root/miniconda3/envs/wikidyk/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 269, in launch_agent
+    raise ChildFailedError(
+torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
+============================================================
+src/train.py FAILED
+------------------------------------------------------------
+Failures:
+  <NO_OTHER_FAILURES>
+------------------------------------------------------------
+Root Cause (first observed failure):
+[0]:
+  time      : 2025-05-13_01:06:34
+  host      : bb9aa167977b
+  rank      : 0 (local_rank: 0)
+  exitcode  : 1 (pid: 443141)
+  error_file: <N/A>
+  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
+============================================================
+[2025-05-13 01:06:34] ERROR: Training failed for roberta-large with exit code 1
+[2025-05-13 01:06:34] ERROR: Training failed for roberta-large with exit code 1
+[2025-05-13 01:06:34] Check error log for details: train_results/roberta-large_ds100_upsample1000/20250513_005845.log
+[2025-05-13 01:06:34] Resource usage after training roberta-large:
+[2025-05-13 01:06:34] GPU memory usage:
+42903 MiB, 81920 MiB
+37603 MiB, 81920 MiB
+26205 MiB, 81920 MiB
+26205 MiB, 81920 MiB
+[2025-05-13 01:06:34] Disk space usage for model outputs:
+16K	train_results/roberta-large_ds100_upsample1000
+[2025-05-13 01:06:34] 
+[2025-05-13 01:06:34] All training runs completed at Tue May 13 01:06:34 UTC 2025
+[2025-05-13 01:06:34] =======================================
+[2025-05-13 01:06:34] Summary of training runs:
+[2025-05-13 01:06:34] Model | Status | Duration | Output Size

20250513_010808.log

@@ -0,0 +1,73 @@
+[2025-05-13 01:17:09] Created output directory: train_results/roberta-large_ds100_upsample1000
+[2025-05-13 01:17:09] Chat mode disabled
+[2025-05-13 01:17:09] Model size is 3B or smaller (0 B). Using full fine-tuning.
+[2025-05-13 01:17:10] Adjusted parameters for roberta model:
+[2025-05-13 01:17:10]   - LEARNING_RATE: 1e-5
+[2025-05-13 01:17:10]   - BATCH_SIZE: 64
+[2025-05-13 01:17:10]   - GRADIENT_ACCUMULATION_STEPS: 1
+[2025-05-13 01:17:10] No QA format data will be used
+[2025-05-13 01:17:10] Limiting dataset size to: 100 samples
+[2025-05-13 01:17:10] =======================================
+[2025-05-13 01:17:10] Starting training for model: roberta-large
+[2025-05-13 01:17:10] =======================================
+[2025-05-13 01:17:10] CUDA_VISIBLE_DEVICES: 2,3
+[2025-05-13 01:17:10] WANDB_PROJECT: wikidyk-ar
+[2025-05-13 01:17:10] DATA_PATH: data/wikidyk2022-2025_01082025_gpt-4o_evalv2_pages_formatted_combined_v2.json
+[2025-05-13 01:17:10] Global Batch Size: 128
+[2025-05-13 01:17:10] Data Size: 100
+[2025-05-13 01:17:10] Executing command: torchrun --nproc_per_node "2" --master-port 29501 src/train.py       --model_name_or_path "roberta-large"       --data_path "data/wikidyk2022-2025_01082025_gpt-4o_evalv2_pages_formatted_combined_v2.json"       --output_dir "train_results/roberta-large_ds100_upsample1000"       --num_upsample "1000"       --per_device_train_batch_size "64"       --gradient_accumulation_steps "1"       --learning_rate "1e-5"       --num_train_epochs "1"       --model_max_length "32768"       --report_to wandb --logging_steps 50 --save_strategy no       --bf16 True --use_flash_attention_2 True       --qa_data_ratio "-1"       --predict_mask "false"                            --ds_size 100
+[2025-05-13 01:17:10] Training started at Tue May 13 01:17:10 UTC 2025
+W0513 01:17:11.276000 445420 site-packages/torch/distributed/run.py:792] 
+W0513 01:17:11.276000 445420 site-packages/torch/distributed/run.py:792] *****************************************
+W0513 01:17:11.276000 445420 site-packages/torch/distributed/run.py:792] 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. 
+W0513 01:17:11.276000 445420 site-packages/torch/distributed/run.py:792] *****************************************
+WARNING:root:Output directory: train_results/roberta-large_ds100_upsample1000
+WARNING:root:Loading data...
+WARNING:root:Output directory: train_results/roberta-large_ds100_upsample1000
+WARNING:root:Loading data...
+WARNING:root:Dataset initialized with all QA data:
+WARNING:root:  - 0 QA examples
+WARNING:root:  - 100 fact examples with upsampling factor 1000
+WARNING:root:  - Total examples: 100000
+/root/yuwei/WikiDYKEvalV2/src/train.py:119: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
+  trainer = Trainer(model=model, tokenizer=tokenizer, args=training_args, **data_module)
+WARNING:root:Dataset initialized with all QA data:
+WARNING:root:  - 0 QA examples
+WARNING:root:  - 100 fact examples with upsampling factor 1000
+WARNING:root:  - Total examples: 100000
+/root/yuwei/WikiDYKEvalV2/src/train.py:119: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.
+  trainer = Trainer(model=model, tokenizer=tokenizer, args=training_args, **data_module)
+wandb: WARNING The `run_name` is currently set to the same value as `TrainingArguments.output_dir`. If this was not intended, please specify a different run name by setting the `TrainingArguments.run_name` parameter.
+wandb: Currently logged in as: yuweiz to https://api.wandb.ai. Use `wandb login --relogin` to force relogin
+wandb: Tracking run with wandb version 0.19.11
+wandb: Run data is saved locally in /root/yuwei/WikiDYKEvalV2/wandb/run-20250513_011722-r26z7i58
+wandb: Run `wandb offline` to turn off syncing.
+wandb: Syncing run train_results/roberta-large_ds100_upsample1000
+wandb: ⭐️ View project at https://wandb.ai/yuweiz/wikidyk-ar
+wandb: 🚀 View run at https://wandb.ai/yuweiz/wikidyk-ar/runs/r26z7i58
+
  0%|          | 0/782 [00:00<?, ?it/s][rank1]:[W513 01:17:23.343224380 reducer.cpp:1400] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
+[rank0]:[W513 01:17:23.361164336 reducer.cpp:1400] Warning: find_unused_parameters=True was specified in DDP constructor, but did not find any unused parameters in the forward pass. This flag results in an extra traversal of the autograd graph every iteration,  which can adversely affect performance. If your model indeed never has any unused parameters in the forward pass, consider turning this flag off. Note that this warning may be a false positive if your model has flow control causing later iterations to have unused parameters. (function operator())
+
  0%|          | 1/782 [00:00<08:54,  1.46it/s]
  0%|          | 2/782 [00:00<05:27,  2.38it/s]
  0%|          | 3/782 [00:01<04:19,  3.01it/s]
  1%|          | 4/782 [00:01<04:34,  2.83it/s]
  1%|          | 5/782 [00:01<04:01,  3.22it/s]
  1%|          | 6/782 [00:02<03:52,  3.34it/s]
  1%|          | 7/782 [00:02<03:36,  3.58it/s]
  1%|          | 8/782 [00:02<03:23,  3.80it/s]
  1%|          | 9/782 [00:02<03:38,  3.53it/s]
  1%|▏         | 10/782 [00:03<03:28,  3.71it/s]
  1%|▏         | 11/782 [00:03<03:52,  3.32it/s]
  2%|▏         | 12/782 [00:03<03:33,  3.60it/s]
  2%|▏         | 13/782 [00:04<03:51,  3.32it/s]
  2%|▏         | 14/782 [00:04<03:38,  3.51it/s]
  2%|▏         | 15/782 [00:04<03:34,  3.58it/s]
  2%|▏         | 16/782 [00:04<03:27,  3.69it/s]
  2%|▏         | 17/782 [00:05<03:16,  3.89it/s]
  2%|▏         | 18/782 [00:05<03:36,  3.52it/s]
  2%|▏         | 19/782 [00:05<03:31,  3.61it/s]
  3%|▎         | 20/782 [00:05<03:25,  3.71it/s]
  3%|▎         | 21/782 [00:06<03:30,  3.61it/s]
  3%|▎         | 22/782 [00:06<03:20,  3.80it/s]
  3%|▎         | 23/782 [00:06<03:14,  3.90it/s]
  3%|▎         | 24/782 [00:06<03:24,  3.71it/s]
  3%|▎         | 25/782 [00:07<03:17,  3.84it/s]
  3%|▎         | 26/782 [00:07<03:33,  3.55it/s]
  3%|▎         | 27/782 [00:07<03:19,  3.78it/s]
  4%|▎         | 28/782 [00:08<03:22,  3.72it/s]
  4%|▎         | 29/782 [00:08<03:21,  3.73it/s]
  4%|▍         | 30/782 [00:08<03:21,  3.74it/s]
  4%|▍         | 31/782 [00:08<03:32,  3.54it/s]
  4%|▍         | 32/782 [00:09<03:18,  3.78it/s]
  4%|▍         | 33/782 [00:09<03:15,  3.84it/s]
  4%|▍         | 34/782 [00:09<03:20,  3.73it/s]
  4%|▍         | 35/782 [00:09<03:17,  3.79it/s]
  5%|▍         | 36/782 [00:10<03:18,  3.75it/s]
  5%|▍         | 37/782 [00:10<03:27,  3.59it/s]
  5%|▍         | 38/782 [00:10<03:18,  3.75it/s]
  5%|▍         | 39/782 [00:10<03:15,  3.80it/s]
  5%|▌         | 40/782 [00:11<03:19,  3.72it/s]
  5%|▌         | 41/782 [00:11<03:16,  3.76it/s]
  5%|▌         | 42/782 [00:11<03:31,  3.50it/s]
  5%|▌         | 43/782 [00:12<03:20,  3.68it/s]
  6%|▌         | 44/782 [00:12<03:21,  3.67it/s]
  6%|▌         | 45/782 [00:12<03:23,  3.62it/s]
  6%|▌         | 46/782 [00:12<03:20,  3.68it/s]
  6%|▌         | 47/782 [00:13<03:19,  3.68it/s]
  6%|▌         | 48/782 [00:13<03:20,  3.67it/s]
  6%|▋         | 49/782 [00:13<03:06,  3.92it/s]
  6%|▋         | 50/782 [00:14<03:30,  3.48it/s]
                                                
  6%|▋         | 50/782 [00:14<03:30,  3.48it/s]
+
  7%|▋         | 51/782 [00:14<03:21,  3.63it/s]
  7%|▋         | 52/782 [00:14<03:38,  3.33it/s]
  7%|▋         | 53/782 [00:14<03:25,  3.55it/s]
  7%|▋         | 54/782 [00:15<03:16,  3.70it/s]
  7%|▋         | 55/782 [00:15<03:11,  3.79it/s]
  7%|▋         | 56/782 [00:15<03:02,  3.97it/s]
  7%|▋         | 57/782 [00:15<03:11,  3.79it/s]
  7%|▋         | 58/782 [00:16<03:14,  3.73it/s]
  8%|▊         | 59/782 [00:16<03:14,  3.72it/s]
  8%|▊         | 60/782 [00:16<03:06,  3.86it/s]
  8%|▊         | 61/782 [00:16<03:06,  3.88it/s]
  8%|▊         | 62/782 [00:17<03:03,  3.93it/s]
  8%|▊         | 63/782 [00:17<03:06,  3.86it/s]
  8%|▊         | 64/782 [00:17<03:06,  3.84it/s]
  8%|▊         | 65/782 [00:17<02:58,  4.01it/s]
  8%|▊         | 66/782 [00:18<03:03,  3.90it/s]
  9%|▊         | 67/782 [00:18<03:06,  3.84it/s]
  9%|▊         | 68/782 [00:18<03:08,  3.79it/s]
  9%|▉         | 69/782 [00:19<03:18,  3.58it/s]
  9%|▉         | 70/782 [00:19<03:07,  3.81it/s]
  9%|▉         | 71/782 [00:19<03:34,  3.32it/s]
  9%|▉         | 72/782 [00:19<03:19,  3.56it/s]
  9%|▉         | 73/782 [00:20<03:36,  3.28it/s]
  9%|▉         | 74/782 [00:20<03:18,  3.58it/s]
 10%|▉         | 75/782 [00:20<03:32,  3.33it/s]
 10%|▉         | 76/782 [00:21<03:27,  3.40it/s]
 10%|▉         | 77/782 [00:21<03:16,  3.60it/s]
 10%|▉         | 78/782 [00:21<03:24,  3.45it/s]
 10%|█         | 79/782 [00:21<03:08,  3.72it/s]
 10%|█         | 80/782 [00:22<03:03,  3.83it/s]
 10%|█         | 81/782 [00:22<03:05,  3.79it/s]
 10%|█         | 82/782 [00:22<03:00,  3.88it/s]
 11%|█         | 83/782 [00:22<03:23,  3.44it/s]
 11%|█         | 84/782 [00:23<03:10,  3.67it/s]
 11%|█         | 85/782 [00:23<03:08,  3.70it/s]
 11%|█         | 86/782 [00:23<03:09,  3.67it/s]
 11%|█         | 87/782 [00:24<03:05,  3.74it/s]
 11%|█▏        | 88/782 [00:24<03:12,  3.61it/s]
 11%|█▏        | 89/782 [00:24<03:03,  3.78it/s]
 12%|█▏        | 90/782 [00:24<03:02,  3.78it/s]
 12%|█���        | 91/782 [00:25<03:06,  3.70it/s]
 12%|█▏        | 92/782 [00:25<03:06,  3.71it/s]
 12%|█▏        | 93/782 [00:25<03:12,  3.57it/s]
 12%|█▏        | 94/782 [00:25<03:02,  3.77it/s]
 12%|█▏        | 95/782 [00:26<02:57,  3.86it/s]
 12%|█▏        | 96/782 [00:26<03:06,  3.68it/s]
 12%|█▏        | 97/782 [00:26<03:03,  3.73it/s]
 13%|█▎        | 98/782 [00:26<03:02,  3.75it/s]
 13%|█▎        | 99/782 [00:27<03:01,  3.77it/s]
 13%|█▎        | 100/782 [00:27<02:52,  3.96it/s]
                                                 
+
 13%|█▎        | 100/782 [00:27<02:52,  3.96it/s]
 13%|█▎        | 101/782 [00:27<02:55,  3.88it/s]
 13%|█▎        | 102/782 [00:27<02:52,  3.95it/s]
 13%|█▎        | 103/782 [00:28<02:54,  3.89it/s]
 13%|█▎        | 104/782 [00:28<02:48,  4.03it/s]
 13%|█▎        | 105/782 [00:28<02:44,  4.12it/s]
 14%|█▎        | 106/782 [00:28<02:49,  3.98it/s]
 14%|█▎        | 107/782 [00:29<02:48,  4.00it/s]
 14%|█▍        | 108/782 [00:29<03:18,  3.40it/s]
 14%|█▍        | 109/782 [00:29<03:02,  3.68it/s]
 14%|█▍        | 110/782 [00:30<02:53,  3.86it/s]
 14%|█▍        | 111/782 [00:30<03:29,  3.20it/s]
 14%|█▍        | 112/782 [00:30<03:13,  3.47it/s]
 14%|█▍        | 113/782 [00:31<03:09,  3.53it/s]
 15%|█▍        | 114/782 [00:31<02:59,  3.73it/s]
 15%|█▍        | 115/782 [00:31<02:51,  3.90it/s]
 15%|█▍        | 116/782 [00:31<02:52,  3.86it/s]
 15%|█▍        | 117/782 [00:31<02:53,  3.83it/s]
 15%|█▌        | 118/782 [00:32<02:53,  3.82it/s]
 15%|█▌        | 119/782 [00:32<02:56,  3.75it/s]
 15%|█▌        | 120/782 [00:32<02:46,  3.97it/s]
 15%|█▌        | 121/782 [00:32<02:43,  4.04it/s]
 16%|█▌        | 122/782 [00:33<03:02,  3.62it/s]
 16%|█▌        | 123/782 [00:33<02:55,  3.76it/s]
 16%|█▌        | 124/782 [00:33<03:08,  3.49it/s]
 16%|█▌        | 125/782 [00:34<02:55,  3.75it/s]
 16%|█▌        | 126/782 [00:34<02:48,  3.90it/s]
 16%|█▌        | 127/782 [00:34<02:58,  3.66it/s]
 16%|█▋        | 128/782 [00:34<02:51,  3.82it/s]
 16%|█▋        | 129/782 [00:35<02:53,  3.75it/s]
 17%|█▋        | 130/782 [00:35<02:49,  3.85it/s]
 17%|█▋        | 131/782 [00:35<02:48,  3.87it/s]
 17%|█▋        | 132/782 [00:35<02:48,  3.85it/s]
 17%|█▋        | 133/782 [00:36<02:44,  3.95it/s]
 17%|█▋        | 134/782 [00:36<02:57,  3.65it/s]
 17%|█▋        | 135/782 [00:36<02:53,  3.73it/s]
 17%|█▋        | 136/782 [00:37<02:55,  3.68it/s]
 18%|█▊        | 137/782 [00:37<02:52,  3.73it/s]
 18%|█▊        | 138/782 [00:37<02:57,  3.62it/s]
 18%|█▊        | 139/782 [00:37<02:52,  3.72it/s]
 18%|█▊        | 140/782 [00:38<02:44,  3.90it/s]
 18%|█▊        | 141/782 [00:38<02:54,  3.68it/s]
 18%|█▊        | 142/782 [00:38<02:48,  3.80it/s]
 18%|█▊        | 143/782 [00:39<03:16,  3.26it/s]
 18%|█▊        | 144/782 [00:39<03:02,  3.50it/s]
 19%|█▊        | 145/782 [00:39<03:06,  3.42it/s]
 19%|█▊        | 146/782 [00:39<02:59,  3.54it/s]
 19%|█▉        | 147/782 [00:40<02:51,  3.69it/s]
 19%|█▉        | 148/782 [00:40<02:49,  3.75it/s]
 19%|█▉        | 149/782 [00:40<02:37,  4.01it/s]
 19%|█▉        | 150/782 [00:40<02:38,  3.98it/s]
                                                 
+
 19%|█▉        | 150/782 [00:40<02:38,  3.98it/s]
 19%|█▉        | 151/782 [00:41<02:47,  3.77it/s]
 19%|█▉        | 152/782 [00:41<02:41,  3.91it/s]
 20%|█▉        | 153/782 [00:41<02:55,  3.57it/s]
 20%|█▉        | 154/782 [00:41<02:43,  3.83it/s]
 20%|█▉        | 155/782 [00:42<02:40,  3.90it/s]
 20%|█▉        | 156/782 [00:42<02:49,  3.70it/s]
 20%|██        | 157/782 [00:42<02:42,  3.85it/s]
 20%|██        | 158/782 [00:42<02:43,  3.82it/s]
 20%|██        | 159/782 [00:43<02:37,  3.96it/s]
 20%|██        | 160/782 [00:43<02:31,  4.10it/s]
 21%|██        | 161/782 [00:43<02:36,  3.98it/s]
 21%|██        | 162/782 [00:43<02:32,  4.06it/s]
 21%|██        | 163/782 [00:44<02:38,  3.89it/s]
 21%|██        | 164/782 [00:44<02:40,  3.85it/s]
 21%|██        | 165/782 [00:44<02:31,  4.07it/s]
 21%|██        | 166/782 [00:44<02:35,  3.97it/s]
 21%|██▏       | 167/782 [00:45<02:34,  3.98it/s]
 21%|██▏       | 168/782 [00:45<02:37,  3.90it/s]
 22%|██▏       | 169/782 [00:45<02:41,  3.79it/s]
 22%|██▏       | 170/782 [00:45<02:32,  4.02it/s]
 22%|██▏       | 171/782 [00:46<02:50,  3.59it/s]
 22%|██▏       | 172/782 [00:46<02:43,  3.73it/s]
 22%|██▏       | 173/782 [00:46<02:54,  3.49it/s]
 22%|██▏       | 174/782 [00:47<02:43,  3.72it/s]
 22%|██▏       | 175/782 [00:47<02:39,  3.80it/s]
 23%|██▎       | 176/782 [00:47<02:44,  3.68it/s]
 23%|██▎       | 177/782 [00:47<02:42,  3.73it/s]
 23%|██▎       | 178/782 [00:48<02:49,  3.56it/s]
 23%|██▎       | 179/782 [00:48<02:36,  3.86it/s]
 23%|██▎       | 180/782 [00:48<02:44,  3.65it/s]
 23%|██▎       | 181/782 [00:48<02:41,  3.72it/s]
 23%|██▎       | 182/782 [00:49<02:37,  3.81it/s]
 23%|██▎       | 183/782 [00:49<02:39,  3.75it/s]
 24%|██▎       | 184/782 [00:49<02:32,  3.93it/s]
 24%|██▎       | 185/782 [00:50<02:45,  3.62it/s]
 24%|██▍       | 186/782 [00:50<02:40,  3.71it/s]
 24%|██▍       | 187/782 [00:50<02:45,  3.60it/s]
 24%|██▍       | 188/782 [00:50<02:41,  3.67it/s]
 24%|██▍       | 189/782 [00:51<02:31,  3.91it/s]
 24%|██▍       | 190/782 [00:51<02:32,  3.87it/s]
 24%|██▍       | 191/782 [00:51<02:30,  3.92it/s]
 25%|██▍       | 192/782 [00:51<02:38,  3.71it/s]
 25%|██▍       | 193/782 [00:52<02:41,  3.66it/s]
 25%|██▍       | 194/782 [00:52<02:30,  3.90it/s]
 25%|██▍       | 195/782 [00:52<02:30,  3.89it/s]
 25%|██▌       | 196/782 [00:52<02:26,  3.99it/s]
 25%|██▌       | 197/782 [00:53<02:28,  3.94it/s]
 25%|██▌       | 198/782 [00:53<02:36,  3.72it/s]
 25%|██▌       | 199/782 [00:53<02:31,  3.85it/s]
 26%|██▌       | 200/782 [00:53<02:33,  3.79it/s]
                                                 
+
 26%|██▌       | 200/782 [00:54<02:33,  3.79it/s]
 26%|██▌       | 201/782 [00:54<02:39,  3.65it/s]
 26%|██▌       | 202/782 [00:54<02:34,  3.76it/s]
 26%|██▌       | 203/782 [00:54<02:36,  3.71it/s]
 26%|██▌       | 204/782 [00:55<02:28,  3.90it/s]
 26%|██▌       | 205/782 [00:55<02:22,  4.04it/s]
 26%|██▋       | 206/782 [00:55<02:26,  3.94it/s]
 26%|██▋       | 207/782 [00:55<02:23,  4.00it/s]
 27%|██▋       | 208/782 [00:56<02:27,  3.90it/s]
 27%|██▋       | 209/782 [00:56<02:23,  4.00it/s]
 27%|██▋       | 210/782 [00:56<02:32,  3.74it/s]
 27%|██▋       | 211/782 [00:56<02:28,  3.86it/s]
 27%|██▋       | 212/782 [00:57<02:28,  3.85it/s]
 27%|██▋       | 213/782 [00:57<02:23,  3.96it/s]
 27%|██▋       | 214/782 [00:57<02:19,  4.08it/s]
 27%|██▋       | 215/782 [00:57<02:22,  3.98it/s]
 28%|██▊       | 216/782 [00:58<02:22,  3.96it/s]
 28%|██▊       | 217/782 [00:58<02:25,  3.89it/s]
 28%|██▊       | 218/782 [00:58<02:29,  3.78it/s]
 28%|██▊       | 219/782 [00:58<02:19,  4.03it/s]
 28%|██▊       | 220/782 [00:59<02:21,  3.96it/s]
 28%|██▊       | 221/782 [00:59<02:25,  3.86it/s]
 28%|██▊       | 222/782 [00:59<02:24,  3.88it/s]
 29%|██▊       | 223/782 [00:59<02:29,  3.75it/s]
 29%|██▊       | 224/782 [01:00<02:21,  3.95it/s]
 29%|██▉       | 225/782 [01:00<02:36,  3.55it/s]
 29%|██▉       | 226/782 [01:00<02:33,  3.62it/s]
 29%|██▉       | 227/782 [01:00<02:32,  3.64it/s]
 29%|██▉       | 228/782 [01:01<02:33,  3.61it/s]
 29%|██▉       | 229/782 [01:01<02:22,  3.89it/s]
 29%|██▉       | 230/782 [01:01<02:21,  3.91it/s]
 30%|██▉       | 231/782 [01:02<02:25,  3.80it/s]
 30%|██▉       | 232/782 [01:02<02:23,  3.82it/s]
 30%|██▉       | 233/782 [01:02<02:28,  3.69it/s]
 30%|██▉       | 234/782 [01:02<02:20,  3.89it/s]
 30%|███       | 235/782 [01:03<02:21,  3.85it/s]
 30%|███       | 236/782 [01:03<02:19,  3.92it/s]
 30%|███       | 237/782 [01:03<02:28,  3.68it/s]
 30%|███       | 238/782 [01:03<02:23,  3.79it/s]
 31%|███       | 239/782 [01:04<02:16,  3.96it/s]
 31%|███       | 240/782 [01:04<02:29,  3.61it/s]
 31%|███       | 241/782 [01:04<02:24,  3.75it/s]
 31%|███       | 242/782 [01:04<02:28,  3.63it/s]
 31%|███       | 243/782 [01:05<02:22,  3.79it/s]
 31%|███       | 244/782 [01:05<02:18,  3.88it/s]
 31%|███▏      | 245/782 [01:05<02:20,  3.83it/s]
 31%|███▏      | 246/782 [01:05<02:18,  3.86it/s]
 32%|███▏      | 247/782 [01:06<02:16,  3.91it/s]
 32%|███▏      | 248/782 [01:06<02:21,  3.77it/s]
 32%|███▏      | 249/782 [01:06<02:16,  3.90it/s]
 32%|███▏      | 250/782 [01:06<02:15,  3.93it/s]
                                                 
+
 32%|███▏      | 250/782 [01:07<02:15,  3.93it/s]
 32%|███▏      | 251/782 [01:07<02:20,  3.77it/s]
 32%|███▏      | 252/782 [01:07<02:18,  3.82it/s]
 32%|███▏      | 253/782 [01:07<02:20,  3.76it/s]
 32%|███▏      | 254/782 [01:08<02:22,  3.70it/s]
 33%|███▎      | 255/782 [01:08<02:21,  3.72it/s]
 33%|███▎      | 256/782 [01:08<02:18,  3.80it/s]
 33%|███▎      | 257/782 [01:08<02:17,  3.83it/s]
 33%|███▎      | 258/782 [01:09<02:20,  3.73it/s]
 33%|███▎      | 259/782 [01:09<02:13,  3.92it/s]
 33%|███▎      | 260/782 [01:09<02:12,  3.95it/s]
 33%|███▎      | 261/782 [01:09<02:15,  3.83it/s]
 34%|███▎      | 262/782 [01:10<02:15,  3.85it/s]
 34%|███▎      | 263/782 [01:10<02:24,  3.60it/s]
 34%|███▍      | 264/782 [01:10<02:18,  3.73it/s]
 34%|███▍      | 265/782 [01:10<02:14,  3.85it/s]
 34%|███▍      | 266/782 [01:11<02:16,  3.78it/s]
 34%|███▍      | 267/782 [01:11<02:11,  3.93it/s]
 34%|███▍      | 268/782 [01:11<02:15,  3.80it/s]
 34%|███▍      | 269/782 [01:11<02:09,  3.95it/s]
 35%|███▍      | 270/782 [01:12<02:05,  4.07it/s]
 35%|███▍      | 271/782 [01:12<02:10,  3.92it/s]
 35%|███▍      | 272/782 [01:12<02:06,  4.04it/s]
 35%|███▍      | 273/782 [01:13<02:16,  3.72it/s]
 35%|███▌      | 274/782 [01:13<02:08,  3.94it/s]
 35%|███▌      | 275/782 [01:13<02:05,  4.03it/s]
 35%|███▌      | 276/782 [01:13<02:12,  3.80it/s]
 35%|███▌      | 277/782 [01:14<02:09,  3.89it/s]
 36%|███▌      | 278/782 [01:14<02:16,  3.70it/s]
 36%|███▌      | 279/782 [01:14<02:25,  3.46it/s]
 36%|███▌      | 280/782 [01:14<02:13,  3.75it/s]
 36%|███▌      | 281/782 [01:15<02:14,  3.73it/s]
 36%|███▌      | 282/782 [01:15<02:13,  3.74it/s]
 36%|███▌      | 283/782 [01:15<02:12,  3.78it/s]
 36%|███▋      | 284/782 [01:16<02:25,  3.41it/s]
 36%|███▋      | 285/782 [01:16<02:16,  3.64it/s]
 37%|███▋      | 286/782 [01:16<02:12,  3.75it/s]
 37%|███▋      | 287/782 [01:16<02:08,  3.84it/s]
 37%|███▋      | 288/782 [01:17<02:15,  3.64it/s]
 37%|███▋      | 289/782 [01:17<02:11,  3.74it/s]
 37%|███▋      | 290/782 [01:17<02:06,  3.87it/s]
 37%|███▋      | 291/782 [01:17<02:08,  3.82it/s]
 37%|███▋      | 292/782 [01:18<02:05,  3.89it/s]
 37%|███▋      | 293/782 [01:18<02:18,  3.54it/s]
 38%|███▊      | 294/782 [01:18<02:09,  3.77it/s]
 38%|███▊      | 295/782 [01:18<02:04,  3.90it/s]
 38%|███▊      | 296/782 [01:19<02:06,  3.85it/s]
 38%|███▊      | 297/782 [01:19<02:04,  3.88it/s]
 38%|███▊      | 298/782 [01:19<02:20,  3.44it/s]
 38%|███▊      | 299/782 [01:19<02:08,  3.75it/s]
 38%|███▊      | 300/782 [01:20<02:09,  3.71it/s]
                                                 
+
 38%|███▊      | 300/782 [01:20<02:09,  3.71it/s]
 38%|███▊      | 301/782 [01:20<02:09,  3.72it/s]
 39%|███▊      | 302/782 [01:20<02:05,  3.84it/s]
 39%|███▊      | 303/782 [01:21<02:27,  3.26it/s]
 39%|███▉      | 304/782 [01:21<02:13,  3.58it/s]
 39%|███▉      | 305/782 [01:21<02:11,  3.63it/s]
 39%|███▉      | 306/782 [01:21<02:12,  3.60it/s]
 39%|███▉      | 307/782 [01:22<02:09,  3.67it/s]
 39%|███▉      | 308/782 [01:22<02:13,  3.56it/s]
 40%|███▉      | 309/782 [01:22<02:06,  3.74it/s]
 40%|███▉      | 310/782 [01:22<02:05,  3.75it/s]
 40%|███▉      | 311/782 [01:23<02:01,  3.87it/s]
 40%|███▉      | 312/782 [01:23<01:59,  3.95it/s]
 40%|████      | 313/782 [01:23<02:12,  3.54it/s]
 40%|████      | 314/782 [01:24<02:04,  3.75it/s]
 40%|████      | 315/782 [01:24<02:11,  3.54it/s]
 40%|████      | 316/782 [01:24<02:06,  3.68it/s]
 41%|████      | 317/782 [01:24<02:06,  3.67it/s]
 41%|████      | 318/782 [01:25<02:07,  3.63it/s]
 41%|████      | 319/782 [01:25<02:02,  3.78it/s]
 41%|████      | 320/782 [01:25<02:01,  3.81it/s]
 41%|████      | 321/782 [01:25<01:59,  3.87it/s]
 41%|████      | 322/782 [01:26<02:08,  3.57it/s]
 41%|████▏     | 323/782 [01:26<02:01,  3.79it/s]
 41%|████▏     | 324/782 [01:26<01:58,  3.85it/s]
 42%|████▏     | 325/782 [01:26<01:59,  3.84it/s]
 42%|████▏     | 326/782 [01:27<01:55,  3.96it/s]
 42%|████▏     | 327/782 [01:27<01:59,  3.82it/s]
 42%|████▏     | 328/782 [01:27<01:54,  3.96it/s]
 42%|████▏     | 329/782 [01:27<01:52,  4.04it/s]
 42%|████▏     | 330/782 [01:28<01:56,  3.87it/s]
 42%|████▏     | 331/782 [01:28<01:52,  4.00it/s]
 42%|████▏     | 332/782 [01:28<02:07,  3.54it/s]
 43%|████▎     | 333/782 [01:29<02:01,  3.71it/s]
 43%|████▎     | 334/782 [01:29<02:01,  3.68it/s]
 43%|████▎     | 335/782 [01:29<02:01,  3.69it/s]
 43%|████▎     | 336/782 [01:29<02:01,  3.69it/s]
 43%|████▎     | 337/782 [01:30<02:06,  3.52it/s]
 43%|████▎     | 338/782 [01:30<01:58,  3.76it/s]
 43%|████▎     | 339/782 [01:30<01:54,  3.88it/s]
 43%|████▎     | 340/782 [01:30<01:57,  3.77it/s]
 44%|████▎     | 341/782 [01:31<01:58,  3.74it/s]
 44%|████▎     | 342/782 [01:31<01:56,  3.77it/s]
 44%|████▍     | 343/782 [01:31<01:59,  3.67it/s]
 44%|████▍     | 344/782 [01:32<01:52,  3.88it/s]
 44%|████▍     | 345/782 [01:32<02:04,  3.51it/s]
 44%|████▍     | 346/782 [01:32<02:00,  3.60it/s]
 44%|████▍     | 347/782 [01:33<02:14,  3.24it/s]
 45%|████▍     | 348/782 [01:33<02:01,  3.56it/s]
 45%|████▍     | 349/782 [01:33<01:55,  3.76it/s]
 45%|████▍     | 350/782 [01:33<01:58,  3.64it/s]
                                                 
+
 45%|████▍     | 350/782 [01:33<01:58,  3.64it/s]
 45%|████▍     | 351/782 [01:34<01:56,  3.71it/s]
 45%|████▌     | 352/782 [01:34<01:57,  3.67it/s]
 45%|████▌     | 353/782 [01:34<02:00,  3.56it/s]
 45%|████▌     | 354/782 [01:34<01:52,  3.81it/s]
 45%|████▌     | 355/782 [01:35<01:54,  3.73it/s]
 46%|████▌     | 356/782 [01:35<01:50,  3.85it/s]
 46%|████▌     | 357/782 [01:35<01:51,  3.83it/s]
 46%|████▌     | 358/782 [01:35<01:52,  3.77it/s]
 46%|████▌     | 359/782 [01:36<01:45,  4.02it/s]
 46%|████▌     | 360/782 [01:36<01:47,  3.94it/s]
 46%|████▌     | 361/782 [01:36<01:48,  3.88it/s]
 46%|████▋     | 362/782 [01:36<01:46,  3.94it/s]
 46%|████▋     | 363/782 [01:37<02:03,  3.39it/s]
 47%|████▋     | 364/782 [01:37<01:57,  3.55it/s]
 47%|████▋     | 365/782 [01:37<01:52,  3.69it/s]
 47%|████▋     | 366/782 [01:38<02:06,  3.30it/s]
 47%|████▋     | 367/782 [01:38<01:57,  3.54it/s]
 47%|████▋     | 368/782 [01:38<01:55,  3.57it/s]
 47%|████▋     | 369/782 [01:38<01:51,  3.70it/s]
 47%|████▋     | 370/782 [01:39<01:46,  3.88it/s]
 47%|████▋     | 371/782 [01:39<01:56,  3.52it/s]
 48%|████▊     | 372/782 [01:39<01:52,  3.64it/s]
 48%|████▊     | 373/782 [01:39<01:51,  3.68it/s]
 48%|████▊     | 374/782 [01:40<01:47,  3.80it/s]
 48%|████▊     | 375/782 [01:40<01:46,  3.84it/s]
 48%|████▊     | 376/782 [01:40<01:58,  3.42it/s]
 48%|████▊     | 377/782 [01:41<01:50,  3.65it/s]
 48%|████▊     | 378/782 [01:41<01:54,  3.53it/s]
 48%|████▊     | 379/782 [01:41<01:48,  3.72it/s]
 49%|████▊     | 380/782 [01:42<02:07,  3.15it/s]
 49%|████▊     | 381/782 [01:42<01:57,  3.41it/s]
 49%|████▉     | 382/782 [01:42<02:05,  3.20it/s]
 49%|████▉     | 383/782 [01:42<01:54,  3.50it/s]
 49%|████▉     | 384/782 [01:43<01:50,  3.62it/s]
 49%|████▉     | 385/782 [01:43<01:48,  3.65it/s]
 49%|████▉     | 386/782 [01:43<01:43,  3.82it/s]
 49%|████▉     | 387/782 [01:43<01:46,  3.70it/s]
 50%|████▉     | 388/782 [01:44<01:43,  3.82it/s]
 50%|████▉     | 389/782 [01:44<01:41,  3.87it/s]
 50%|████▉     | 390/782 [01:44<01:44,  3.73it/s]
 50%|█████     | 391/782 [01:44<01:41,  3.83it/s]
 50%|█████     | 392/782 [01:45<01:54,  3.42it/s]
 50%|█████     | 393/782 [01:45<01:44,  3.71it/s]
 50%|█████     | 394/782 [01:45<01:44,  3.70it/s]
 51%|█████     | 395/782 [01:46<01:43,  3.74it/s]
 51%|█████     | 396/782 [01:46<01:38,  3.90it/s]
 51%|█████     | 397/782 [01:46<01:41,  3.79it/s]
 51%|█████     | 398/782 [01:46<01:35,  4.01it/s]
 51%|█████     | 399/782 [01:46<01:32,  4.14it/s]
 51%|█████     | 400/782 [01:47<01:36,  3.97it/s]
                                                 
+
 51%|█████     | 400/782 [01:47<01:36,  3.97it/s]
 51%|█████▏    | 401/782 [01:47<01:34,  4.04it/s]
 51%|█████▏    | 402/782 [01:47<01:37,  3.89it/s]
 52%|█████▏    | 403/782 [01:48<01:33,  4.05it/s]
 52%|█████▏    | 404/782 [01:48<01:32,  4.07it/s]
 52%|█████▏    | 405/782 [01:48<01:37,  3.89it/s]
 52%|█████▏    | 406/782 [01:48<01:37,  3.87it/s]
 52%|█████▏    | 407/782 [01:49<01:38,  3.80it/s]
 52%|█████▏    | 408/782 [01:49<01:34,  3.96it/s]
 52%|█████▏    | 409/782 [01:49<01:32,  4.05it/s]
 52%|█████▏    | 410/782 [01:49<01:42,  3.62it/s]
 53%|█████▎    | 411/782 [01:50<01:39,  3.72it/s]
 53%|█████▎    | 412/782 [01:50<01:40,  3.67it/s]
 53%|█████▎    | 413/782 [01:50<01:44,  3.51it/s]
 53%|█████▎    | 414/782 [01:50<01:40,  3.67it/s]
 53%|█████▎    | 415/782 [01:51<01:38,  3.71it/s]
 53%|█████▎    | 416/782 [01:51<01:40,  3.66it/s]
 53%|█████▎    | 417/782 [01:51<01:38,  3.72it/s]
 53%|█████▎    | 418/782 [01:52<01:39,  3.68it/s]
 54%|█████▎    | 419/782 [01:52<01:39,  3.65it/s]
 54%|█████▎    | 420/782 [01:52<01:33,  3.89it/s]
 54%|█████▍    | 421/782 [01:52<01:45,  3.43it/s]
 54%|█████▍    | 422/782 [01:53<01:40,  3.60it/s]
 54%|█████▍    | 423/782 [01:53<01:39,  3.62it/s]
 54%|█████▍    | 424/782 [01:53<01:34,  3.80it/s]
 54%|█████▍    | 425/782 [01:53<01:31,  3.92it/s]
 54%|█████▍    | 426/782 [01:54<01:39,  3.59it/s]
 55%|█████▍    | 427/782 [01:54<01:34,  3.76it/s]
 55%|█████▍    | 428/782 [01:54<01:35,  3.72it/s]
 55%|█████▍    | 429/782 [01:54<01:32,  3.82it/s]
 55%|█████▍    | 430/782 [01:55<01:34,  3.73it/s]
 55%|█████▌    | 431/782 [01:55<01:33,  3.77it/s]
 55%|█████▌    | 432/782 [01:55<01:31,  3.83it/s]
 55%|█████▌    | 433/782 [01:56<01:34,  3.68it/s]
 55%|█████▌    | 434/782 [01:56<01:28,  3.92it/s]
 56%|█████▌    | 435/782 [01:56<01:30,  3.85it/s]
 56%|█████▌    | 436/782 [01:56<01:28,  3.91it/s]
 56%|█████▌    | 437/782 [01:57<01:29,  3.85it/s]
 56%|█████▌    | 438/782 [01:57<01:26,  3.99it/s]
 56%|█████▌    | 439/782 [01:57<01:24,  4.07it/s]
 56%|█████▋    | 440/782 [01:57<01:30,  3.76it/s]
 56%|█████▋    | 441/782 [01:58<01:28,  3.84it/s]
 57%|█████▋    | 442/782 [01:58<01:31,  3.73it/s]
 57%|█████▋    | 443/782 [01:58<01:26,  3.93it/s]
 57%|█████▋    | 444/782 [01:58<01:24,  3.99it/s]
 57%|█████▋    | 445/782 [01:59<01:29,  3.78it/s]
 57%|█████▋    | 446/782 [01:59<01:26,  3.88it/s]
 57%|█████▋    | 447/782 [01:59<01:30,  3.69it/s]
 57%|█████▋    | 448/782 [01:59<01:27,  3.83it/s]
 57%|█████▋    | 449/782 [02:00<01:24,  3.93it/s]
 58%|█████▊    | 450/782 [02:00<01:26,  3.85it/s]
                                                 
+
 58%|█████▊    | 450/782 [02:00<01:26,  3.85it/s]
 58%|█████▊    | 451/782 [02:00<01:24,  3.92it/s]
 58%|█████▊    | 452/782 [02:01<01:30,  3.65it/s]
 58%|█████▊    | 453/782 [02:01<01:26,  3.81it/s]
 58%|█████▊    | 454/782 [02:01<01:23,  3.91it/s]
 58%|█████▊    | 455/782 [02:01<01:25,  3.84it/s]
 58%|█████▊    | 456/782 [02:02<01:24,  3.86it/s]
 58%|█████▊    | 457/782 [02:02<01:25,  3.80it/s]
 59%|█████▊    | 458/782 [02:02<01:25,  3.78it/s]
 59%|█████▊    | 459/782 [02:02<01:20,  4.00it/s]
 59%|█████▉    | 460/782 [02:03<01:21,  3.96it/s]
 59%|█████▉    | 461/782 [02:03<01:25,  3.77it/s]
 59%|█████▉    | 462/782 [02:03<01:21,  3.92it/s]
 59%|█████▉    | 463/782 [02:03<01:22,  3.88it/s]
 59%|█████▉    | 464/782 [02:04<01:19,  3.99it/s]
 59%|█████▉    | 465/782 [02:04<01:18,  4.06it/s]
 60%|█████▉    | 466/782 [02:04<01:20,  3.91it/s]
 60%|█████▉    | 467/782 [02:04<01:19,  3.98it/s]
 60%|█████▉    | 468/782 [02:05<01:27,  3.59it/s]
 60%|█████▉    | 469/782 [02:05<01:21,  3.84it/s]
 60%|██████    | 470/782 [02:05<01:18,  3.98it/s]
 60%|██████    | 471/782 [02:05<01:21,  3.80it/s]
 60%|██████    | 472/782 [02:06<01:19,  3.90it/s]
 60%|██████    | 473/782 [02:06<01:21,  3.79it/s]
 61%|██████    | 474/782 [02:06<01:28,  3.47it/s]
 61%|██████    | 475/782 [02:06<01:22,  3.73it/s]
 61%|██████    | 476/782 [02:07<01:21,  3.74it/s]
 61%|██████    | 477/782 [02:07<01:21,  3.75it/s]
 61%|██████    | 478/782 [02:07<01:20,  3.76it/s]
 61%|██████▏   | 479/782 [02:08<01:27,  3.48it/s]
 61%|██████▏   | 480/782 [02:08<01:20,  3.77it/s]
 62%|██████▏   | 481/782 [02:08<01:20,  3.76it/s]
 62%|██████▏   | 482/782 [02:08<01:19,  3.75it/s]
 62%|██████▏   | 483/782 [02:09<01:20,  3.72it/s]
 62%|██████▏   | 484/782 [02:09<01:20,  3.68it/s]
 62%|██████▏   | 485/782 [02:09<01:15,  3.93it/s]
 62%|██████▏   | 486/782 [02:09<01:22,  3.61it/s]
 62%|██████▏   | 487/782 [02:10<01:19,  3.70it/s]
 62%|██████▏   | 488/782 [02:10<01:18,  3.73it/s]
 63%|██████▎   | 489/782 [02:10<01:19,  3.69it/s]
 63%|██████▎   | 490/782 [02:10<01:14,  3.90it/s]
 63%|██████▎   | 491/782 [02:11<01:16,  3.80it/s]
 63%|██████▎   | 492/782 [02:11<01:14,  3.89it/s]
 63%|██████▎   | 493/782 [02:11<01:25,  3.39it/s]
 63%|██████▎   | 494/782 [02:12<01:19,  3.64it/s]
 63%|██████▎   | 495/782 [02:12<01:15,  3.80it/s]
 63%|██████▎   | 496/782 [02:12<01:18,  3.63it/s]
 64%|██████▎   | 497/782 [02:12<01:15,  3.78it/s]
 64%|██████▎   | 498/782 [02:13<01:21,  3.49it/s]
 64%|██████▍   | 499/782 [02:13<01:15,  3.76it/s]
 64%|██████▍   | 500/782 [02:13<01:15,  3.74it/s]
                                                 
+
 64%|██████▍   | 500/782 [02:13<01:15,  3.74it/s]
 64%|██████▍   | 501/782 [02:13<01:14,  3.76it/s]
 64%|██████▍   | 502/782 [02:14<01:15,  3.70it/s]
 64%|██████▍   | 503/782 [02:14<01:13,  3.80it/s]
 64%|██████▍   | 504/782 [02:14<01:12,  3.85it/s]
 65%|██████▍   | 505/782 [02:15<01:11,  3.85it/s]
 65%|██████▍   | 506/782 [02:15<01:10,  3.90it/s]
 65%|██████▍   | 507/782 [02:15<01:11,  3.85it/s]
 65%|██████▍   | 508/782 [02:15<01:07,  4.04it/s]
 65%|██████▌   | 509/782 [02:16<01:17,  3.53it/s]
 65%|██████▌   | 510/782 [02:16<01:13,  3.72it/s]
 65%|██████▌   | 511/782 [02:16<01:18,  3.44it/s]
 65%|██████▌   | 512/782 [02:16<01:12,  3.73it/s]
 66%|██████▌   | 513/782 [02:17<01:11,  3.74it/s]
 66%|██████▌   | 514/782 [02:17<01:13,  3.66it/s]
 66%|██████▌   | 515/782 [02:17<01:12,  3.70it/s]
 66%|██████▌   | 516/782 [02:18<01:14,  3.58it/s]
 66%|██████▌   | 517/782 [02:18<01:09,  3.82it/s]
 66%|██████▌   | 518/782 [02:18<01:09,  3.79it/s]
 66%|██████▋   | 519/782 [02:18<01:07,  3.91it/s]
 66%|██████▋   | 520/782 [02:19<01:08,  3.83it/s]
 67%|██████▋   | 521/782 [02:19<01:04,  4.02it/s]
 67%|██████▋   | 522/782 [02:19<01:03,  4.09it/s]
 67%|██████▋   | 523/782 [02:19<01:06,  3.91it/s]
 67%|██████▋   | 524/782 [02:20<01:06,  3.86it/s]
 67%|██████▋   | 525/782 [02:20<01:10,  3.66it/s]
 67%|██████▋   | 526/782 [02:20<01:06,  3.86it/s]
 67%|██████▋   | 527/782 [02:20<01:04,  3.94it/s]
 68%|██████▊   | 528/782 [02:21<01:06,  3.80it/s]
 68%|██████▊   | 529/782 [02:21<01:04,  3.89it/s]
 68%|██████▊   | 530/782 [02:21<01:05,  3.86it/s]
 68%|██████▊   | 531/782 [02:21<01:01,  4.06it/s]
 68%|██████▊   | 532/782 [02:22<01:04,  3.89it/s]
 68%|██████▊   | 533/782 [02:22<01:04,  3.84it/s]
 68%|██████▊   | 534/782 [02:22<01:02,  3.99it/s]
 68%|██████▊   | 535/782 [02:22<01:03,  3.86it/s]
 69%|██████▊   | 536/782 [02:23<01:01,  4.00it/s]
 69%|██████▊   | 537/782 [02:23<00:59,  4.09it/s]
 69%|██████▉   | 538/782 [02:23<01:02,  3.92it/s]
 69%|██████▉   | 539/782 [02:23<01:01,  3.94it/s]
 69%|██████▉   | 540/782 [02:24<01:03,  3.79it/s]
 69%|██████▉   | 541/782 [02:24<01:02,  3.88it/s]
 69%|██████▉   | 542/782 [02:24<01:01,  3.92it/s]
 69%|██████▉   | 543/782 [02:24<01:02,  3.83it/s]
 70%|██████▉   | 544/782 [02:25<01:01,  3.87it/s]
 70%|██████▉   | 545/782 [02:25<01:05,  3.64it/s]
 70%|██████▉   | 546/782 [02:25<01:01,  3.82it/s]
 70%|██████▉   | 547/782 [02:26<01:04,  3.66it/s]
 70%|███████   | 548/782 [02:26<01:02,  3.73it/s]
 70%|███████   | 549/782 [02:26<00:59,  3.89it/s]
 70%|███████   | 550/782 [02:26<01:08,  3.38it/s]
                                                 
+
 70%|███████   | 550/782 [02:26<01:08,  3.38it/s]
 70%|███████   | 551/782 [02:27<01:05,  3.52it/s]
 71%|███████   | 552/782 [02:27<01:06,  3.45it/s]
 71%|███████   | 553/782 [02:27<01:05,  3.48it/s]
 71%|███████   | 554/782 [02:27<01:01,  3.69it/s]
 71%|███████   | 555/782 [02:28<01:02,  3.66it/s]
 71%|███████   | 556/782 [02:28<00:59,  3.77it/s]
 71%|███████   | 557/782 [02:28<00:59,  3.79it/s]
 71%|███████▏  | 558/782 [02:28<00:58,  3.82it/s]
 71%|███████▏  | 559/782 [02:29<00:57,  3.88it/s]
 72%|███████▏  | 560/782 [02:29<01:00,  3.68it/s]
 72%|███████▏  | 561/782 [02:29<00:57,  3.86it/s]
 72%|███████▏  | 562/782 [02:30<00:58,  3.76it/s]
 72%|███████▏  | 563/782 [02:30<00:57,  3.81it/s]
 72%|███████▏  | 564/782 [02:30<00:56,  3.89it/s]
 72%|███████▏  | 565/782 [02:30<01:01,  3.51it/s]
 72%|███████▏  | 566/782 [02:31<00:58,  3.71it/s]
 73%|███████▎  | 567/782 [02:31<00:58,  3.65it/s]
 73%|███████▎  | 568/782 [02:31<00:56,  3.76it/s]
 73%|███████▎  | 569/782 [02:31<00:57,  3.68it/s]
 73%|███████▎  | 570/782 [02:32<00:57,  3.66it/s]
 73%|███████▎  | 571/782 [02:32<00:54,  3.86it/s]
 73%|███████▎  | 572/782 [02:32<00:57,  3.62it/s]
 73%|██████��▎  | 573/782 [02:33<00:55,  3.75it/s]
 73%|███████▎  | 574/782 [02:33<00:56,  3.69it/s]
 74%|███████▎  | 575/782 [02:33<00:56,  3.68it/s]
 74%|███████▎  | 576/782 [02:33<00:52,  3.94it/s]
 74%|███████▍  | 577/782 [02:34<00:56,  3.66it/s]
 74%|███████▍  | 578/782 [02:34<00:53,  3.78it/s]
 74%|███████▍  | 579/782 [02:34<00:53,  3.77it/s]
 74%|███████▍  | 580/782 [02:34<00:50,  3.97it/s]
 74%|███████▍  | 581/782 [02:35<00:49,  4.09it/s]
 74%|███████▍  | 582/782 [02:35<00:51,  3.87it/s]
 75%|███████▍  | 583/782 [02:35<00:50,  3.93it/s]
 75%|███████▍  | 584/782 [02:35<00:49,  3.96it/s]
 75%|███████▍  | 585/782 [02:36<00:53,  3.66it/s]
 75%|███████▍  | 586/782 [02:36<00:52,  3.75it/s]
 75%|███████▌  | 587/782 [02:36<00:53,  3.65it/s]
 75%|███████▌  | 588/782 [02:36<00:50,  3.81it/s]
 75%|███████▌  | 589/782 [02:37<00:49,  3.87it/s]
 75%|███████▌  | 590/782 [02:37<00:48,  3.93it/s]
 76%|███████▌  | 591/782 [02:37<00:46,  4.10it/s]
 76%|███████▌  | 592/782 [02:38<00:53,  3.52it/s]
 76%|███████▌  | 593/782 [02:38<00:51,  3.70it/s]
 76%|███████▌  | 594/782 [02:38<00:51,  3.66it/s]
 76%|███████▌  | 595/782 [02:38<00:49,  3.76it/s]
 76%|███████▌  | 596/782 [02:39<00:48,  3.80it/s]
 76%|███████▋  | 597/782 [02:39<00:47,  3.86it/s]
 76%|███████▋  | 598/782 [02:39<00:47,  3.89it/s]
 77%|███████▋  | 599/782 [02:39<00:46,  3.97it/s]
 77%|███████▋  | 600/782 [02:40<00:43,  4.14it/s]
                                                 
+
 77%|███████▋  | 600/782 [02:40<00:43,  4.14it/s]
 77%|███████▋  | 601/782 [02:40<00:45,  3.93it/s]
 77%|███████▋  | 602/782 [02:40<00:45,  3.96it/s]
 77%|███████▋  | 603/782 [02:40<00:46,  3.84it/s]
 77%|███████▋  | 604/782 [02:41<00:51,  3.44it/s]
 77%|███████▋  | 605/782 [02:41<00:48,  3.65it/s]
 77%|███████▋  | 606/782 [02:41<00:47,  3.71it/s]
 78%|███████▊  | 607/782 [02:41<00:47,  3.68it/s]
 78%|███████▊  | 608/782 [02:42<00:46,  3.77it/s]
 78%|███████▊  | 609/782 [02:42<00:49,  3.48it/s]
 78%|███████▊  | 610/782 [02:42<00:46,  3.67it/s]
 78%|███████▊  | 611/782 [02:43<00:46,  3.70it/s]
 78%|███████▊  | 612/782 [02:43<00:45,  3.73it/s]
 78%|███████▊  | 613/782 [02:43<00:44,  3.78it/s]
 79%|███████▊  | 614/782 [02:43<00:44,  3.78it/s]
 79%|███████▊  | 615/782 [02:44<00:41,  3.98it/s]
 79%|███████▉  | 616/782 [02:44<00:42,  3.89it/s]
 79%|███████▉  | 617/782 [02:44<00:42,  3.92it/s]
 79%|███████▉  | 618/782 [02:44<00:41,  3.97it/s]
 79%|███████▉  | 619/782 [02:45<00:42,  3.84it/s]
 79%|███████▉  | 620/782 [02:45<00:41,  3.93it/s]
 79%|███████▉  | 621/782 [02:45<00:41,  3.84it/s]
 80%|███████▉  | 622/782 [02:45<00:41,  3.86it/s]
 80%|███████▉  | 623/782 [02:46<00:39,  4.03it/s]
 80%|███████▉  | 624/782 [02:46<00:42,  3.73it/s]
 80%|███████▉  | 625/782 [02:46<00:39,  3.97it/s]
 80%|████████  | 626/782 [02:46<00:38,  4.05it/s]
 80%|████████  | 627/782 [02:47<00:46,  3.31it/s]
 80%|████████  | 628/782 [02:47<00:43,  3.54it/s]
 80%|████████  | 629/782 [02:47<00:45,  3.36it/s]
 81%|████████  | 630/782 [02:48<00:41,  3.68it/s]
 81%|████████  | 631/782 [02:48<00:40,  3.72it/s]
 81%|████████  | 632/782 [02:48<00:40,  3.74it/s]
 81%|████████  | 633/782 [02:48<00:42,  3.53it/s]
 81%|████████  | 634/782 [02:49<00:39,  3.74it/s]
 81%|████████  | 635/782 [02:49<00:38,  3.82it/s]
 81%|████████▏ | 636/782 [02:49<00:39,  3.74it/s]
 81%|████████▏ | 637/782 [02:49<00:37,  3.86it/s]
 82%|████████▏ | 638/782 [02:50<00:45,  3.18it/s]
 82%|████████▏ | 639/782 [02:50<00:42,  3.40it/s]
 82%|████████▏ | 640/782 [02:50<00:39,  3.57it/s]
 82%|████████▏ | 641/782 [02:51<00:39,  3.58it/s]
 82%|████████▏ | 642/782 [02:51<00:37,  3.70it/s]
 82%|████████▏ | 643/782 [02:51<00:39,  3.51it/s]
 82%|████████▏ | 644/782 [02:51<00:37,  3.68it/s]
 82%|████████▏ | 645/782 [02:52<00:37,  3.69it/s]
 83%|████████▎ | 646/782 [02:52<00:35,  3.81it/s]
 83%|███��████▎ | 647/782 [02:52<00:35,  3.80it/s]
 83%|████████▎ | 648/782 [02:52<00:34,  3.86it/s]
 83%|████████▎ | 649/782 [02:53<00:33,  4.02it/s]
 83%|████████▎ | 650/782 [02:53<00:33,  3.95it/s]
                                                 
+
 83%|████████▎ | 650/782 [02:53<00:33,  3.95it/s]
 83%|████████▎ | 651/782 [02:53<00:34,  3.80it/s]
 83%|████████▎ | 652/782 [02:54<00:34,  3.71it/s]
 84%|████████▎ | 653/782 [02:54<00:35,  3.61it/s]
 84%|████████▎ | 654/782 [02:54<00:33,  3.80it/s]
 84%|████████▍ | 655/782 [02:54<00:35,  3.55it/s]
 84%|████████▍ | 656/782 [02:55<00:34,  3.67it/s]
 84%|████████▍ | 657/782 [02:55<00:34,  3.66it/s]
 84%|████████▍ | 658/782 [02:55<00:36,  3.36it/s]
 84%|████████▍ | 659/782 [02:55<00:33,  3.64it/s]
 84%|████████▍ | 660/782 [02:56<00:33,  3.68it/s]
 85%|████████▍ | 661/782 [02:56<00:33,  3.66it/s]
 85%|████████▍ | 662/782 [02:56<00:32,  3.73it/s]
 85%|████████▍ | 663/782 [02:57<00:34,  3.49it/s]
 85%|████████▍ | 664/782 [02:57<00:31,  3.79it/s]
 85%|████████▌ | 665/782 [02:57<00:29,  3.91it/s]
 85%|████████▌ | 666/782 [02:57<00:30,  3.74it/s]
 85%|████████▌ | 667/782 [02:58<00:30,  3.81it/s]
 85%|████████▌ | 668/782 [02:58<00:30,  3.76it/s]
 86%|████████▌ | 669/782 [02:58<00:28,  3.93it/s]
 86%|████████▌ | 670/782 [02:58<00:28,  3.98it/s]
 86%|████████▌ | 671/782 [02:59<00:30,  3.63it/s]
 86%|████████▌ | 672/782 [02:59<00:29,  3.73it/s]
 86%|████████▌ | 673/782 [02:59<00:29,  3.74it/s]
 86%|████████▌ | 674/782 [02:59<00:27,  3.90it/s]
 86%|████████▋ | 675/782 [03:00<00:26,  4.00it/s]
 86%|████████▋ | 676/782 [03:00<00:29,  3.59it/s]
 87%|████████▋ | 677/782 [03:00<00:28,  3.74it/s]
 87%|████████▋ | 678/782 [03:01<00:27,  3.73it/s]
 87%|████████▋ | 679/782 [03:01<00:28,  3.56it/s]
 87%|████████▋ | 680/782 [03:01<00:27,  3.70it/s]
 87%|████████▋ | 681/782 [03:01<00:27,  3.72it/s]
 87%|████████▋ | 682/782 [03:02<00:26,  3.75it/s]
 87%|████████▋ | 683/782 [03:02<00:25,  3.85it/s]
 87%|████████▋ | 684/782 [03:02<00:24,  3.96it/s]
 88%|████████▊ | 685/782 [03:02<00:23,  4.08it/s]
 88%|████████▊ | 686/782 [03:03<00:26,  3.65it/s]
 88%|████████▊ | 687/782 [03:03<00:24,  3.84it/s]
 88%|████████▊ | 688/782 [03:03<00:24,  3.78it/s]
 88%|████████▊ | 689/782 [03:03<00:24,  3.87it/s]
 88%|████████▊ | 690/782 [03:04<00:23,  3.97it/s]
 88%|████████▊ | 691/782 [03:04<00:24,  3.65it/s]
 88%|████████▊ | 692/782 [03:04<00:23,  3.76it/s]
 89%|████████▊ | 693/782 [03:04<00:23,  3.82it/s]
 89%|████████▊ | 694/782 [03:05<00:23,  3.73it/s]
 89%|████████▉ | 695/782 [03:05<00:21,  4.00it/s]
 89%|████████▉ | 696/782 [03:05<00:23,  3.66it/s]
 89%|████████▉ | 697/782 [03:06<00:22,  3.77it/s]
 89%|████████▉ | 698/782 [03:06<00:23,  3.53it/s]
 89%|████████▉ | 699/782 [03:06<00:22,  3.72it/s]
 90%|████████▉ | 700/782 [03:06<00:21,  3.73it/s]
                                                 
+
 90%|████████▉ | 700/782 [03:06<00:21,  3.73it/s]
 90%|████████▉ | 701/782 [03:07<00:21,  3.81it/s]
 90%|████████▉ | 702/782 [03:07<00:20,  3.88it/s]
 90%|████████▉ | 703/782 [03:07<00:20,  3.90it/s]
 90%|█████████ | 704/782 [03:07<00:19,  4.09it/s]
 90%|█████████ | 705/782 [03:08<00:19,  3.97it/s]
 90%|█████████ | 706/782 [03:08<00:19,  3.98it/s]
 90%|█████████ | 707/782 [03:08<00:19,  3.83it/s]
 91%|█████████ | 708/782 [03:08<00:20,  3.67it/s]
 91%|█████████ | 709/782 [03:09<00:18,  3.92it/s]
 91%|█████████ | 710/782 [03:09<00:18,  3.89it/s]
 91%|█████████ | 711/782 [03:09<00:18,  3.82it/s]
 91%|█████████ | 712/782 [03:09<00:17,  3.98it/s]
 91%|█████████ | 713/782 [03:10<00:20,  3.44it/s]
 91%|█████████▏| 714/782 [03:10<00:18,  3.69it/s]
 91%|█████████▏| 715/782 [03:10<00:17,  3.77it/s]
 92%|█████████▏| 716/782 [03:11<00:17,  3.76it/s]
 92%|█████████▏| 717/782 [03:11<00:17,  3.81it/s]
 92%|█████████▏| 718/782 [03:11<00:17,  3.58it/s]
 92%|█████████▏| 719/782 [03:11<00:16,  3.73it/s]
 92%|█████████▏| 720/782 [03:12<00:16,  3.70it/s]
 92%|█████████▏| 721/782 [03:12<00:16,  3.75it/s]
 92%|█████████▏| 722/782 [03:12<00:15,  3.87it/s]
 92%|█████████▏| 723/782 [03:12<00:15,  3.72it/s]
 93%|█████████▎| 724/782 [03:13<00:14,  3.94it/s]
 93%|█████████▎| 725/782 [03:13<00:17,  3.34it/s]
 93%|█████████▎| 726/782 [03:13<00:15,  3.53it/s]
 93%|█████████▎| 727/782 [03:14<00:17,  3.23it/s]
 93%|█████████▎| 728/782 [03:14<00:15,  3.48it/s]
 93%|█████████▎| 729/782 [03:14<00:14,  3.68it/s]
 93%|█████████▎| 730/782 [03:14<00:14,  3.70it/s]
 93%|█████████▎| 731/782 [03:15<00:13,  3.77it/s]
 94%|█████████▎| 732/782 [03:15<00:12,  3.93it/s]
 94%|█████████▎| 733/782 [03:15<00:13,  3.58it/s]
 94%|█████████▍| 734/782 [03:15<00:12,  3.71it/s]
 94%|█████████▍| 735/782 [03:16<00:12,  3.84it/s]
 94%|█████████▍| 736/782 [03:16<00:12,  3.78it/s]
 94%|█████████▍| 737/782 [03:16<00:11,  3.76it/s]
 94%|█████████▍| 738/782 [03:17<00:11,  3.69it/s]
 95%|█████████▍| 739/782 [03:17<00:11,  3.87it/s]
 95%|█████████▍| 740/782 [03:17<00:10,  3.97it/s]
 95%|█████████▍| 741/782 [03:17<00:10,  3.91it/s]
 95%|█████████▍| 742/782 [03:18<00:10,  3.81it/s]
 95%|█████████▌| 743/782 [03:18<00:10,  3.57it/s]
 95%|█████████▌| 744/782 [03:18<00:10,  3.77it/s]
 95%|█████████▌| 745/782 [03:18<00:09,  3.91it/s]
 95%|█████████▌| 746/782 [03:19<00:09,  3.82it/s]
 96%|█████████▌| 747/782 [03:19<00:09,  3.77it/s]
 96%|█████████▌| 748/782 [03:19<00:10,  3.30it/s]
 96%|█████████▌| 749/782 [03:19<00:09,  3.55it/s]
 96%|█████████▌| 750/782 [03:20<00:10,  3.11it/s]
                                                 
+
 96%|█████████▌| 750/782 [03:20<00:10,  3.11it/s]
 96%|█████████▌| 751/782 [03:20<00:09,  3.26it/s]
 96%|█████████▌| 752/782 [03:20<00:09,  3.25it/s]
 96%|█████████▋| 753/782 [03:21<00:08,  3.54it/s]
 96%|█████████▋| 754/782 [03:21<00:07,  3.66it/s]
 97%|█████████▋| 755/782 [03:21<00:07,  3.51it/s]
 97%|█████████▋| 756/782 [03:22<00:07,  3.64it/s]
 97%|█████████▋| 757/782 [03:22<00:07,  3.44it/s]
 97%|█████████▋| 758/782 [03:22<00:06,  3.72it/s]
 97%|█████████▋| 759/782 [03:22<00:07,  3.19it/s]
 97%|█████████▋| 760/782 [03:23<00:06,  3.43it/s]
 97%|█████████▋| 761/782 [03:23<00:06,  3.40it/s]
 97%|█████████▋| 762/782 [03:23<00:05,  3.67it/s]
 98%|█████████▊| 763/782 [03:23<00:04,  3.81it/s]
 98%|█████████▊| 764/782 [03:24<00:04,  3.80it/s]
 98%|█████████▊| 765/782 [03:24<00:04,  3.87it/s]
 98%|█████████▊| 766/782 [03:24<00:04,  3.92it/s]
 98%|█████████▊| 767/782 [03:25<00:03,  3.87it/s]
 98%|█████████▊| 768/782 [03:25<00:03,  4.03it/s]
 98%|█████████▊| 769/782 [03:25<00:03,  3.53it/s]
 98%|█████████▊| 770/782 [03:25<00:03,  3.73it/s]
 99%|█████████▊| 771/782 [03:26<00:03,  3.61it/s]
 99%|█████████▊| 772/782 [03:26<00:02,  3.81it/s]
 99%|█████████▉| 773/782 [03:26<00:02,  3.93it/s]
 99%|█████████▉| 774/782 [03:26<00:02,  3.53it/s]
 99%|█████████▉| 775/782 [03:27<00:01,  3.68it/s]
 99%|█████████▉| 776/782 [03:27<00:01,  3.29it/s]
 99%|█████████▉| 777/782 [03:27<00:01,  3.52it/s]
 99%|█████████▉| 778/782 [03:28<00:01,  3.79it/s]
                                                 
+
+
+
+
+
+
+
+

README.md

@@ -0,0 +1,57 @@
+---
+library_name: transformers
+license: mit
+base_model: roberta-large
+tags:
+- generated_from_trainer
+model-index:
+- name: roberta-large_ds100_upsample1000
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# roberta-large_ds100_upsample1000
+
+This model is a fine-tuned version of [roberta-large](https://huggingface.co/roberta-large) on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.51.3
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057fca4f594a76a33c8fd9118dc04a2ae8fc0f79eec0f093cd4c959b77425e6f
+size 1421696540

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 32768,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4ff6701ec0170d3ecf8638a70ccb9df6f9ff3db37ed3c06ee3ad1f17c92f02
+size 5368