Saving weights and logs of step 20000

config.json

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "BigBirdForPreTraining"
+    "BigBirdForMaskedLM"
   ],
   "attention_probs_dropout_prob": 0.1,
   "attention_type": "block_sparse",

events.out.tfevents.1626138389.t1v-n-f5c06ea1-w-0.330819.3.v2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38eb5545dae32cb874fc5122bc8138563358f43aa31a60065ed2306bdf775930
+size 2949929

flax_model.msgpack

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:761feeca8b2858e854da0619288bb517206cf43ee56a4f261f9783b9ac1009ea
+size 256576390

wandb/debug-internal.log

@@ -1 +1 @@
-run-20210713_005751-1wnn0lyf/logs/debug-internal.log
+run-20210713_010630-14xhiyhf/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20210713_005751-1wnn0lyf/logs/debug.log
+run-20210713_010630-14xhiyhf/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20210713_005751-1wnn0lyf
+run-20210713_010630-14xhiyhf

wandb/run-20210713_010630-14xhiyhf/files/config.yaml

@@ -0,0 +1,304 @@
+wandb_version: 1
+
+_wandb:
+  desc: null
+  value:
+    cli_version: 0.10.33
+    framework: huggingface
+    huggingface_version: 4.9.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    python_version: 3.8.10
+    t:
+      1:
+      - 3
+      - 11
+      4: 3.8.10
+      5: 0.10.33
+      6: 4.9.0.dev0
+      8:
+      - 5
+adafactor:
+  desc: null
+  value: false
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.98
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+cache_dir:
+  desc: null
+  value: null
+config_name:
+  desc: null
+  value: ./
+dataloader_drop_last:
+  desc: null
+  value: false
+dataloader_num_workers:
+  desc: null
+  value: 0
+dataloader_pin_memory:
+  desc: null
+  value: true
+dataset_config_name:
+  desc: null
+  value: null
+dataset_name:
+  desc: null
+  value: null
+ddp_find_unused_parameters:
+  desc: null
+  value: null
+debug:
+  desc: null
+  value: []
+deepspeed:
+  desc: null
+  value: null
+disable_tqdm:
+  desc: null
+  value: false
+do_eval:
+  desc: null
+  value: false
+do_predict:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: false
+dtype:
+  desc: null
+  value: bfloat16
+eval_accumulation_steps:
+  desc: null
+  value: null
+eval_steps:
+  desc: null
+  value: 92768
+evaluation_strategy:
+  desc: null
+  value: IntervalStrategy.NO
+fp16:
+  desc: null
+  value: false
+fp16_backend:
+  desc: null
+  value: auto
+fp16_full_eval:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+gradient_accumulation_steps:
+  desc: null
+  value: 1
+greater_is_better:
+  desc: null
+  value: null
+group_by_length:
+  desc: null
+  value: false
+ignore_data_skip:
+  desc: null
+  value: false
+label_names:
+  desc: null
+  value: null
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+learning_rate:
+  desc: null
+  value: 5.0e-05
+length_column_name:
+  desc: null
+  value: length
+line_by_line:
+  desc: null
+  value: false
+load_best_model_at_end:
+  desc: null
+  value: false
+local_rank:
+  desc: null
+  value: -1
+log_level:
+  desc: null
+  value: -1
+log_level_replica:
+  desc: null
+  value: -1
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/Jul13_01-05-41_t1v-n-f5c06ea1-w-0
+logging_first_step:
+  desc: null
+  value: false
+logging_steps:
+  desc: null
+  value: 500
+logging_strategy:
+  desc: null
+  value: IntervalStrategy.STEPS
+lr_scheduler_type:
+  desc: null
+  value: SchedulerType.LINEAR
+max_grad_norm:
+  desc: null
+  value: 1.0
+max_seq_length:
+  desc: null
+  value: 4096
+max_steps:
+  desc: null
+  value: -1
+metric_for_best_model:
+  desc: null
+  value: null
+mlm_probability:
+  desc: null
+  value: 0.15
+model_name_or_path:
+  desc: null
+  value: null
+model_type:
+  desc: null
+  value: big_bird
+mp_parameters:
+  desc: null
+  value: ''
+no_cuda:
+  desc: null
+  value: false
+num_train_epochs:
+  desc: null
+  value: 5.0
+output_dir:
+  desc: null
+  value: ./
+overwrite_cache:
+  desc: null
+  value: false
+overwrite_output_dir:
+  desc: null
+  value: true
+pad_to_max_length:
+  desc: null
+  value: false
+past_index:
+  desc: null
+  value: -1
+per_device_eval_batch_size:
+  desc: null
+  value: 2
+per_device_train_batch_size:
+  desc: null
+  value: 2
+per_gpu_eval_batch_size:
+  desc: null
+  value: null
+per_gpu_train_batch_size:
+  desc: null
+  value: null
+prediction_loss_only:
+  desc: null
+  value: false
+preprocessing_num_workers:
+  desc: null
+  value: 64
+push_to_hub:
+  desc: null
+  value: true
+push_to_hub_model_id:
+  desc: null
+  value: ''
+push_to_hub_organization:
+  desc: null
+  value: null
+push_to_hub_token:
+  desc: null
+  value: null
+remove_unused_columns:
+  desc: null
+  value: true
+report_to:
+  desc: null
+  value:
+  - tensorboard
+  - wandb
+resume_from_checkpoint:
+  desc: null
+  value: null
+run_name:
+  desc: null
+  value: ./
+save_on_each_node:
+  desc: null
+  value: false
+save_steps:
+  desc: null
+  value: 20000
+save_strategy:
+  desc: null
+  value: IntervalStrategy.STEPS
+save_total_limit:
+  desc: null
+  value: 5
+seed:
+  desc: null
+  value: 42
+sharded_ddp:
+  desc: null
+  value: []
+skip_memory_metrics:
+  desc: null
+  value: true
+tokenizer_name:
+  desc: null
+  value: ./
+tpu_metrics_debug:
+  desc: null
+  value: false
+tpu_num_cores:
+  desc: null
+  value: null
+train_file:
+  desc: null
+  value: null
+train_ref_file:
+  desc: null
+  value: null
+use_fast_tokenizer:
+  desc: null
+  value: true
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+validation_file:
+  desc: null
+  value: null
+validation_ref_file:
+  desc: null
+  value: null
+validation_split_percentage:
+  desc: null
+  value: 5
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 5000
+weight_decay:
+  desc: null
+  value: 0.0095

wandb/run-20210713_010630-14xhiyhf/files/output.log

@@ -0,0 +1,5410 @@
+/home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:382: UserWarning: jax.host_count has been renamed to jax.process_count. This alias will eventually be removed; please update your code.
+  warnings.warn(
+/home/dat/pino/lib/python3.8/site-packages/jax/lib/xla_bridge.py:369: UserWarning: jax.host_id has been renamed to jax.process_index. This alias will eventually be removed; please update your code.
+  warnings.warn(
+Epoch ... (1/5):   0%|                                    | 0/5 [00:00<?, ?it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   1%|                       | 500/92767 [06:08<14:38:48,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   1%|▏                     | 1000/92767 [10:54<14:33:13,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   2%|▎                     | 1500/92767 [15:40<14:28:03,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   2%|▍                     | 2005/92767 [20:46<43:13:25,  1.71s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   3%|▌                     | 2500/92767 [25:13<14:19:55,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   3%|▋                     | 3000/92767 [29:59<14:13:31,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   4%|▊                    | 3501/92767 [35:04<153:51:07,  6.20s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   4%|▉                     | 4007/92767 [39:51<26:26:24,  1.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   5%|█                      | 4513/92767 [44:38<5:17:18,  4.64it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   5%|█▏                    | 5000/92767 [49:03<13:56:15,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   6%|█▎                    | 5500/92767 [53:49<13:50:21,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   6%|█▍                    | 6000/92767 [58:36<13:45:23,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   7%|█▍                  | 6500/92767 [1:03:22<13:40:53,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   8%|█▌                  | 7003/92767 [1:08:27<73:43:46,  3.09s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   8%|█▌                  | 7500/92767 [1:12:54<13:31:06,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   9%|█▋                  | 8000/92767 [1:17:40<13:26:37,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:   9%|█▊                  | 8503/92767 [1:22:46<72:29:48,  3.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  10%|█▉                  | 9006/92767 [1:27:32<26:20:08,  1.13s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  10%|██▏                  | 9512/92767 [1:32:19<7:27:35,  3.10it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  11%|██                 | 10000/92767 [1:36:45<13:06:55,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  11%|██▏                | 10500/92767 [1:41:31<13:02:26,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  12%|██▎                | 11000/92767 [1:46:17<12:58:46,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  12%|██▎                | 11500/92767 [1:51:03<12:53:11,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  13%|██▍                | 12002/92767 [1:56:09<98:23:42,  4.39s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  13%|██▌                | 12508/92767 [2:00:56<14:34:49,  1.53it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  14%|██▊                 | 13014/92767 [2:05:42<4:42:51,  4.70it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  15%|██▊                | 13500/92767 [2:10:08<12:31:38,  1.76it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  15%|██▊                | 14003/92767 [2:15:13<67:44:48,  3.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  16%|███▏                | 14511/92767 [2:20:00<5:56:33,  3.66it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  16%|███                | 15000/92767 [2:24:26<12:20:02,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  17%|███               | 15501/92767 [2:29:32<133:12:40,  6.21s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  17%|███▎               | 16006/92767 [2:34:18<29:26:21,  1.38s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  18%|███▌                | 16513/92767 [2:39:05<4:37:44,  4.58it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  18%|███▋                | 17018/92767 [2:43:52<3:24:31,  6.17it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  19%|███▌               | 17503/92767 [2:48:36<64:45:38,  3.10s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  19%|███▉                | 18011/92767 [2:53:23<8:05:33,  2.57it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  20%|███▉                | 18515/92767 [2:58:10<3:45:16,  5.49it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  20%|███▉               | 19000/92767 [3:02:35<11:41:57,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  21%|███▉               | 19500/92767 [3:07:21<11:38:06,  1.75it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Training...:  22%|████               | 20000/92767 [3:12:07<11:32:26,  1.75it/s]
+
+git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5)2767 [3:12:27<11:32:26,  1.75it/s]

wandb/run-20210713_010630-14xhiyhf/files/requirements.txt

@@ -0,0 +1,92 @@
+absl-py==0.13.0
+aiohttp==3.7.4.post0
+astunparse==1.6.3
+async-timeout==3.0.1
+attrs==21.2.0
+cachetools==4.2.2
+certifi==2021.5.30
+chardet==4.0.0
+chex==0.0.8
+click==8.0.1
+configparser==5.0.2
+cycler==0.10.0
+datasets==1.9.1.dev0
+dill==0.3.4
+dm-tree==0.1.6
+docker-pycreds==0.4.0
+filelock==3.0.12
+flatbuffers==1.12
+flax==0.3.4
+fsspec==2021.6.1
+gast==0.4.0
+gitdb==4.0.7
+gitpython==3.1.18
+google-auth-oauthlib==0.4.4
+google-auth==1.32.1
+google-pasta==0.2.0
+grpcio==1.34.1
+h5py==3.1.0
+huggingface-hub==0.0.12
+idna==2.10
+jax==0.2.16
+jaxlib==0.1.68
+joblib==1.0.1
+keras-nightly==2.5.0.dev2021032900
+keras-preprocessing==1.1.2
+kiwisolver==1.3.1
+libtpu-nightly==0.1.dev20210615
+markdown==3.3.4
+matplotlib==3.4.2
+msgpack==1.0.2
+multidict==5.1.0
+multiprocess==0.70.12.2
+numpy==1.19.5
+oauthlib==3.1.1
+opt-einsum==3.3.0
+optax==0.0.9
+packaging==21.0
+pandas==1.3.0
+pathtools==0.1.2
+pillow==8.3.1
+pip==20.0.2
+pkg-resources==0.0.0
+promise==2.3
+protobuf==3.17.3
+psutil==5.8.0
+pyarrow==4.0.1
+pyasn1-modules==0.2.8
+pyasn1==0.4.8
+pyparsing==2.4.7
+python-dateutil==2.8.1
+pytz==2021.1
+pyyaml==5.4.1
+regex==2021.7.6
+requests-oauthlib==1.3.0
+requests==2.25.1
+rsa==4.7.2
+sacremoses==0.0.45
+scipy==1.7.0
+sentry-sdk==1.3.0
+setuptools==44.0.0
+shortuuid==1.0.1
+six==1.15.0
+smmap==4.0.0
+subprocess32==3.5.4
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.0
+tensorboard==2.5.0
+tensorflow-estimator==2.5.0
+tensorflow==2.5.0
+termcolor==1.1.0
+tokenizers==0.10.3
+toolz==0.11.1
+tqdm==4.61.2
+transformers==4.9.0.dev0
+typing-extensions==3.7.4.3
+urllib3==1.26.6
+wandb==0.10.33
+werkzeug==2.0.1
+wheel==0.36.2
+wrapt==1.12.1
+xxhash==2.0.2
+yarl==1.6.3

wandb/run-20210713_010630-14xhiyhf/files/wandb-metadata.json

@@ -0,0 +1,44 @@
+{
+    "os": "Linux-5.4.0-1043-gcp-x86_64-with-glibc2.29",
+    "python": "3.8.10",
+    "heartbeatAt": "2021-07-13T01:06:32.665577",
+    "startedAt": "2021-07-13T01:06:30.602414",
+    "docker": null,
+    "cpu_count": 96,
+    "cuda": null,
+    "args": [
+        "--push_to_hub",
+        "--output_dir=./",
+        "--model_type=big_bird",
+        "--config_name=./",
+        "--tokenizer_name=./",
+        "--max_seq_length=4096",
+        "--weight_decay=0.0095",
+        "--warmup_steps=5000",
+        "--overwrite_output_dir",
+        "--adam_beta1=0.9",
+        "--adam_beta2=0.98",
+        "--logging_steps=500",
+        "--eval_steps=92768",
+        "--num_train_epochs=5",
+        "--preprocessing_num_workers=64",
+        "--save_steps=20000",
+        "--learning_rate=5e-5",
+        "--per_device_train_batch_size=2",
+        "--per_device_eval_batch_size=2",
+        "--save_total_limit=5",
+        "--dtype=bfloat16"
+    ],
+    "state": "running",
+    "program": "./run_mlm_flax.py",
+    "codePath": "run_mlm_flax.py",
+    "git": {
+        "remote": "https://huggingface.co/flax-community/pino-roberta-base",
+        "commit": "9bd1fecd26762eebbaa6109a4c76ccc67d6817b3"
+    },
+    "email": null,
+    "root": "/home/dat/pino-roberta-base",
+    "host": "t1v-n-f5c06ea1-w-0",
+    "username": "dat",
+    "executable": "/home/dat/pino/bin/python"
+}

wandb/run-20210713_010630-14xhiyhf/files/wandb-summary.json

@@ -0,0 +1 @@
+{"training_step": 20000, "learning_rate": 4.8365425755036995e-05, "train_loss": 6.714123725891113, "_runtime": 11658, "_timestamp": 1626150048, "_step": 39}

wandb/run-20210713_010630-14xhiyhf/logs/debug.log

@@ -0,0 +1,25 @@
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_setup.py:_flush():69] setting env: {}
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_setup.py:_flush():69] setting login settings: {}
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_init.py:_log_setup():337] Logging user logs to /home/dat/pino-roberta-base/wandb/run-20210713_010630-14xhiyhf/logs/debug.log
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_init.py:_log_setup():338] Logging internal logs to /home/dat/pino-roberta-base/wandb/run-20210713_010630-14xhiyhf/logs/debug-internal.log
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_init.py:init():370] calling init triggers
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_init.py:init():375] wandb.init called with sweep_config: {}
+config: {}
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [wandb_init.py:init():419] starting backend
+2021-07-13 01:06:30,604 INFO    MainThread:330819 [backend.py:_multiprocessing_setup():70] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2021-07-13 01:06:30,660 INFO    MainThread:330819 [backend.py:ensure_launched():135] starting backend process...
+2021-07-13 01:06:30,733 INFO    MainThread:330819 [backend.py:ensure_launched():139] started backend process with pid: 332390
+2021-07-13 01:06:30,735 INFO    MainThread:330819 [wandb_init.py:init():424] backend started and connected
+2021-07-13 01:06:30,738 INFO    MainThread:330819 [wandb_init.py:init():472] updated telemetry
+2021-07-13 01:06:30,739 INFO    MainThread:330819 [wandb_init.py:init():491] communicating current version
+2021-07-13 01:06:31,376 INFO    MainThread:330819 [wandb_init.py:init():496] got version response 
+2021-07-13 01:06:31,377 INFO    MainThread:330819 [wandb_init.py:init():504] communicating run to backend with 30 second timeout
+2021-07-13 01:06:31,567 INFO    MainThread:330819 [wandb_init.py:init():529] starting run threads in backend
+2021-07-13 01:06:32,702 INFO    MainThread:330819 [wandb_run.py:_console_start():1623] atexit reg
+2021-07-13 01:06:32,702 INFO    MainThread:330819 [wandb_run.py:_redirect():1497] redirect: SettingsConsole.REDIRECT
+2021-07-13 01:06:32,703 INFO    MainThread:330819 [wandb_run.py:_redirect():1502] Redirecting console.
+2021-07-13 01:06:32,705 INFO    MainThread:330819 [wandb_run.py:_redirect():1558] Redirects installed.
+2021-07-13 01:06:32,705 INFO    MainThread:330819 [wandb_init.py:init():554] run started, returning control to user process
+2021-07-13 01:06:32,711 INFO    MainThread:330819 [wandb_run.py:_config_callback():872] config_cb None None {'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': False, 'do_predict': False, 'evaluation_strategy': 'IntervalStrategy.NO', 'prediction_loss_only': False, 'per_device_train_batch_size': 2, 'per_device_eval_batch_size': 2, 'per_gpu_train_batch_size': None, 'per_gpu_eval_batch_size': None, 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': None, 'learning_rate': 5e-05, 'weight_decay': 0.0095, 'adam_beta1': 0.9, 'adam_beta2': 0.98, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 5.0, 'max_steps': -1, 'lr_scheduler_type': 'SchedulerType.LINEAR', 'warmup_ratio': 0.0, 'warmup_steps': 5000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jul13_01-05-41_t1v-n-f5c06ea1-w-0', 'logging_strategy': 'IntervalStrategy.STEPS', 'logging_first_step': False, 'logging_steps': 500, 'save_strategy': 'IntervalStrategy.STEPS', 'save_steps': 20000, 'save_total_limit': 5, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'fp16': False, 'fp16_opt_level': 'O1', 'fp16_backend': 'auto', 'fp16_full_eval': False, 'local_rank': -1, 'tpu_num_cores': None, 'tpu_metrics_debug': False, 'debug': [], 'dataloader_drop_last': False, 'eval_steps': 92768, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': None, 'load_best_model_at_end': False, 'metric_for_best_model': None, 'greater_is_better': None, 'ignore_data_skip': False, 'sharded_ddp': [], 'deepspeed': None, 'label_smoothing_factor': 0.0, 'adafactor': False, 'group_by_length': False, 'length_column_name': 'length', 'report_to': ['tensorboard', 'wandb'], 'ddp_find_unused_parameters': None, 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': None, 'push_to_hub_model_id': '', 'push_to_hub_organization': None, 'push_to_hub_token': None, 'mp_parameters': ''}
+2021-07-13 01:06:32,712 INFO    MainThread:330819 [wandb_run.py:_config_callback():872] config_cb None None {'model_name_or_path': None, 'model_type': 'big_bird', 'config_name': './', 'tokenizer_name': './', 'cache_dir': None, 'use_fast_tokenizer': True, 'dtype': 'bfloat16'}
+2021-07-13 01:06:32,714 INFO    MainThread:330819 [wandb_run.py:_config_callback():872] config_cb None None {'dataset_name': None, 'dataset_config_name': None, 'train_file': None, 'validation_file': None, 'train_ref_file': None, 'validation_ref_file': None, 'overwrite_cache': False, 'validation_split_percentage': 5, 'max_seq_length': 4096, 'preprocessing_num_workers': 64, 'mlm_probability': 0.15, 'pad_to_max_length': False, 'line_by_line': False}