|
[16:04:24] - INFO - __main__ - Training/evaluation parameters TrainingArguments( |
|
_n_gpu=-1, |
|
adafactor=False, |
|
adam_beta1=0.9, |
|
adam_beta2=0.999, |
|
adam_epsilon=1e-08, |
|
dataloader_drop_last=False, |
|
dataloader_num_workers=0, |
|
dataloader_pin_memory=True, |
|
ddp_find_unused_parameters=None, |
|
debug=[], |
|
deepspeed=None, |
|
disable_tqdm=False, |
|
do_eval=False, |
|
do_predict=False, |
|
do_train=False, |
|
eval_accumulation_steps=None, |
|
eval_steps=500, |
|
evaluation_strategy=IntervalStrategy.NO, |
|
fp16=False, |
|
fp16_backend=auto, |
|
fp16_full_eval=False, |
|
fp16_opt_level=O1, |
|
gradient_accumulation_steps=1, |
|
greater_is_better=None, |
|
group_by_length=False, |
|
ignore_data_skip=False, |
|
label_names=None, |
|
label_smoothing_factor=0.0, |
|
learning_rate=0.0003, |
|
length_column_name=length, |
|
load_best_model_at_end=False, |
|
local_rank=-1, |
|
log_level=-1, |
|
log_level_replica=-1, |
|
log_on_each_node=True, |
|
logging_dir=./runs/Jul08_16-04-24_t1v-n-112df4a9-w-0, |
|
logging_first_step=False, |
|
logging_steps=500, |
|
logging_strategy=IntervalStrategy.STEPS, |
|
lr_scheduler_type=SchedulerType.LINEAR, |
|
max_grad_norm=1.0, |
|
max_steps=-1, |
|
metric_for_best_model=None, |
|
mp_parameters=, |
|
no_cuda=False, |
|
num_train_epochs=8.0, |
|
output_dir=./, |
|
overwrite_output_dir=True, |
|
past_index=-1, |
|
per_device_eval_batch_size=4, |
|
per_device_train_batch_size=4, |
|
prediction_loss_only=False, |
|
push_to_hub=True, |
|
push_to_hub_model_id=flax-community/roberta-base-mr, |
|
push_to_hub_organization=None, |
|
push_to_hub_token=vdIAyRvCACJNslYtyLHufmNDnUIyknPzUgVDMFiXqJoulvMqjoubonLJzXOJQJczWfRMJumVaMFjGSFVnQAMdswvZkzNIthKrxBeARBXfqnIwjABkKpCbjGEgnkjpjKi, |
|
remove_unused_columns=True, |
|
report_to=[], |
|
resume_from_checkpoint=None, |
|
run_name=./, |
|
save_on_each_node=False, |
|
save_steps=500, |
|
save_strategy=IntervalStrategy.STEPS, |
|
save_total_limit=None, |
|
seed=42, |
|
sharded_ddp=[], |
|
skip_memory_metrics=True, |
|
tpu_metrics_debug=False, |
|
tpu_num_cores=None, |
|
use_legacy_prediction_loop=False, |
|
warmup_ratio=0.0, |
|
warmup_steps=1000, |
|
weight_decay=0.0, |
|
) |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0 |
|
[16:04:24] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2) |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443 |
|
[16:04:24] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0 |
|
[16:04:24] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2) |
|
[16:04:24] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): s3.amazonaws.com:443 |
|
[16:04:25] - DEBUG - urllib3.connectionpool - https://s3.amazonaws.com:443 "HEAD /datasets.huggingface.co/datasets/datasets/oscar/oscar.py HTTP/1.1" 404 0 |
|
[16:04:25] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443 |
|
[16:04:25] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/oscar.py HTTP/1.1" 200 0 |
|
[16:04:25] - DEBUG - urllib3.connectionpool - Starting new HTTPS connection (1): raw.githubusercontent.com:443 |
|
[16:04:25] - DEBUG - urllib3.connectionpool - https://raw.githubusercontent.com:443 "HEAD /huggingface/datasets/master/datasets/oscar/dataset_infos.json HTTP/1.1" 200 0 |
|
[16:04:25] - WARNING - datasets.builder - Reusing dataset oscar (/home/nipunsadvilkar/.cache/huggingface/datasets/oscar/unshuffled_deduplicated_als/1.0.0/84838bd49d2295f62008383b05620571535451d84545037bb94d6f3501651df2) |
|
0%| | 0/5 [00:00<?, ?ba/s]
20%|██ | 1/5 [00:00<00:00, 8.80ba/s]
40%|████ | 2/5 [00:00<00:00, 9.16ba/s]
60%|██████ | 3/5 [00:00<00:00, 9.52ba/s]
80%|████████ | 4/5 [00:00<00:00, 7.13ba/s]
100%|██████████| 5/5 [00:00<00:00, 8.76ba/s] |
|
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 21.45ba/s] |
|
0%| | 0/5 [00:00<?, ?ba/s]
20%|██ | 1/5 [00:00<00:03, 1.32ba/s]
40%|████ | 2/5 [00:01<00:02, 1.24ba/s]
60%|██████ | 3/5 [00:02<00:01, 1.21ba/s]
80%|████████ | 4/5 [00:03<00:00, 1.13ba/s]
100%|██████████| 5/5 [00:03<00:00, 1.43ba/s] |
|
0%| | 0/1 [00:00<?, ?ba/s]
100%|██████████| 1/1 [00:00<00:00, 11.84ba/s] |
|
[16:04:29] - WARNING - __main__ - Unable to display metrics through TensorBoard because the package is not installed: Please run pip install tensorboard to enable. |
|
[16:04:29] - INFO - absl - Starting the local TPU driver. |
|
[16:04:29] - INFO - absl - Unable to initialize backend 'tpu_driver': Not found: Unable to find driver in registry given worker: local:// |
|
[16:04:29] - INFO - absl - Unable to initialize backend 'gpu': Not found: Could not find registered platform with name: "cuda". Available platform names are: Interpreter TPU Host |
|
/home/nipunsadvilkar/roberta_mr_env/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/nipunsadvilkar/roberta_mr_env/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 ... (1/8): 0%| | 0/8 [00:00<?, ?it/s] |
|
Training...: 0%| | 0/142 [00:00<?, ?it/s][A |
|
Training...: 1%| | 1/142 [01:09<2:42:39, 69.21s/it][A |
|
Training...: 4%|▎ | 5/142 [01:09<23:35, 10.33s/it] [A |
|
Training...: 6%|▋ | 9/142 [01:09<10:22, 4.68s/it][A |
|
Training...: 9%|▉ | 13/142 [01:09<05:40, 2.64s/it][A |
|
Training...: 12%|█▏ | 17/142 [01:09<03:23, 1.63s/it][A |
|
Training...: 15%|█▍ | 21/142 [01:09<02:08, 1.06s/it][A |
|
Training...: 18%|█▊ | 25/142 [01:09<01:23, 1.40it/s][A |
|
Training...: 20%|██ | 29/142 [01:10<00:55, 2.04it/s][A |
|
Training...: 23%|██▎ | 33/142 [01:10<00:37, 2.91it/s][A |
|
Training...: 26%|██▌ | 37/142 [01:10<00:25, 4.07it/s][A |
|
Training...: 29%|██▉ | 41/142 [01:10<00:18, 5.60it/s][A |
|
Training...: 32%|███▏ | 45/142 [01:10<00:12, 7.53it/s][A |
|
Training...: 35%|███▍ | 49/142 [01:10<00:09, 9.89it/s][A |
|
Training...: 37%|███▋ | 53/142 [01:10<00:07, 11.55it/s][A |
|
Training...: 40%|████ | 57/142 [01:10<00:05, 14.49it/s][A |
|
Training...: 43%|████▎ | 61/142 [01:11<00:04, 17.61it/s][A |
|
Training...: 46%|████▌ | 65/142 [01:11<00:03, 20.76it/s][A |
|
Training...: 49%|████▊ | 69/142 [01:11<00:03, 23.71it/s][A |
|
Training...: 51%|█████▏ | 73/142 [01:11<00:02, 25.21it/s][A |
|
Training...: 54%|█████▍ | 77/142 [01:11<00:02, 27.38it/s][A |
|
Training...: 57%|█████▋ | 81/142 [01:11<00:02, 29.32it/s][A |
|
Training...: 60%|█████▉ | 85/142 [01:11<00:01, 30.64it/s][A |
|
Training...: 63%|██████▎ | 89/142 [01:11<00:01, 31.96it/s][A |
|
Training...: 65%|██████▌ | 93/142 [01:11<00:01, 32.96it/s][A |
|
Training...: 68%|██████▊ | 97/142 [01:12<00:01, 33.77it/s][A |
|
Training...: 71%|███████ | 101/142 [01:12<00:01, 28.88it/s][A |
|
Training...: 74%|███████▍ | 105/142 [01:12<00:01, 30.53it/s][A |
|
Training...: 77%|███████▋ | 109/142 [01:12<00:01, 31.69it/s][A |
|
Training...: 80%|███████▉ | 113/142 [01:12<00:00, 32.56it/s][A |
|
Training...: 82%|████████▏ | 117/142 [01:12<00:00, 33.33it/s][A |
|
Training...: 85%|████████▌ | 121/142 [01:12<00:00, 33.91it/s][A |
|
Training...: 88%|████████▊ | 125/142 [01:12<00:00, 34.33it/s][A |
|
Training...: 91%|█████████ | 129/142 [01:13<00:00, 34.57it/s][A |
|
Training...: 94%|█████████▎| 133/142 [01:13<00:00, 34.81it/s][A |
|
Training...: 96%|█████████▋| 137/142 [01:13<00:00, 34.79it/s][A |
|
Training...: 99%|█████████▉| 141/142 [01:13<00:00, 34.88it/s][A
Training...: 100%|██████████| 142/142 [01:13<00:00, 1.93it/s] |
|
Epoch ... (1/8): 12%|█▎ | 1/8 [01:15<08:45, 75.01s/it] |
|
Training...: 0%| | 0/142 [00:00<?, ?it/s][A |
|
Training...: 1%|▏ | 2/142 [00:00<00:09, 14.83it/s][A |
|
Training...: 4%|▍ | 6/142 [00:00<00:05, 25.49it/s][A |
|
Training...: 7%|▋ | 10/142 [00:00<00:04, 29.83it/s][A |
|
Training...: 10%|▉ | 14/142 [00:00<00:03, 32.12it/s][A |
|
Training...: 13%|█▎ | 18/142 [00:00<00:03, 33.43it/s][A |
|
Training...: 15%|█▌ | 22/142 [00:00<00:03, 34.49it/s][A |
|
Training...: 18%|█▊ | 26/142 [00:00<00:03, 35.13it/s][A |
|
Training...: 21%|██ | 30/142 [00:00<00:03, 35.34it/s][A |
|
Training...: 24%|██▍ | 34/142 [00:01<00:03, 35.02it/s][A |
|
Training...: 27%|██▋ | 38/142 [00:01<00:02, 34.76it/s][A |
|
Training...: 30%|██▉ | 42/142 [00:01<00:02, 34.71it/s][A |
|
Training...: 32%|███▏ | 46/142 [00:01<00:02, 34.74it/s][A |
|
Training...: 35%|███▌ | 50/142 [00:01<00:03, 29.45it/s][A |
|
Training...: 38%|███▊ | 54/142 [00:01<00:02, 30.62it/s][A |
|
Training...: 41%|████ | 58/142 [00:01<00:02, 32.07it/s][A |
|
Training...: 44%|████▎ | 62/142 [00:01<00:02, 32.46it/s][A |
|
Training...: 46%|████▋ | 66/142 [00:02<00:02, 32.83it/s][A |
|
Training...: 49%|████▉ | 70/142 [00:02<00:02, 33.43it/s][A |
|
Training...: 52%|█████▏ | 74/142 [00:02<00:02, 33.75it/s][A |
|
Training...: 55%|█████▍ | 78/142 [00:02<00:01, 33.50it/s][A |
|
Training...: 58%|█████▊ | 82/142 [00:02<00:01, 33.88it/s][A |
|
Training...: 61%|██████ | 86/142 [00:02<00:01, 34.22it/s][A |
|
Training...: 63%|██████▎ | 90/142 [00:02<00:01, 34.66it/s][A |
|
Training...: 66%|██████▌ | 94/142 [00:02<00:01, 29.58it/s][A |
|
Training...: 69%|██████▉ | 98/142 [00:03<00:01, 31.15it/s][A |
|
Training...: 72%|███████▏ | 102/142 [00:03<00:01, 32.31it/s][A |
|
Training...: 75%|███████▍ | 106/142 [00:03<00:01, 33.06it/s][A |
|
Training...: 77%|███████▋ | 110/142 [00:03<00:00, 33.50it/s][A |
|
Training...: 80%|████████ | 114/142 [00:03<00:00, 34.14it/s][A |
|
Training...: 83%|████████▎ | 118/142 [00:03<00:00, 34.75it/s][A |
|
Training...: 86%|████████▌ | 122/142 [00:03<00:00, 35.06it/s][A |
|
Training...: 89%|████████▊ | 126/142 [00:03<00:00, 35.30it/s][A |
|
Training...: 92%|█████████▏| 130/142 [00:03<00:00, 35.25it/s][A |
|
Training...: 94%|█████████▍| 134/142 [00:04<00:00, 35.33it/s][A |
|
Training...: 97%|█████████▋| 138/142 [00:04<00:00, 35.43it/s][A |
|
Training...: 100%|██████████| 142/142 [00:04<00:00, 29.31it/s][A
Training...: 100%|██████████| 142/142 [00:04<00:00, 32.72it/s] |
|
Epoch ... (1/8): 25%|██▌ | 2/8 [01:20<03:23, 33.88s/it] |
|
Training...: 0%| | 0/142 [00:00<?, ?it/s][A |
|
Training...: 3%|▎ | 4/142 [00:00<00:04, 32.68it/s][A |
|
Training...: 6%|▌ | 8/142 [00:00<00:03, 33.63it/s][A |
|
Training...: 8%|▊ | 12/142 [00:00<00:03, 34.11it/s][A |
|
Training...: 11%|█▏ | 16/142 [00:00<00:03, 34.59it/s][A |
|
Training...: 14%|█▍ | 20/142 [00:00<00:03, 34.64it/s][A |
|
Training...: 17%|█▋ | 24/142 [00:00<00:03, 34.90it/s][A |
|
Training...: 20%|█▉ | 28/142 [00:00<00:03, 35.08it/s][A |
|
Training...: 23%|██▎ | 32/142 [00:00<00:03, 35.12it/s][A |
|
Training...: 25%|██▌ | 36/142 [00:01<00:03, 35.02it/s][A |
|
Training...: 28%|██▊ | 40/142 [00:01<00:02, 34.59it/s][A |
|
Training...: 31%|███ | 44/142 [00:01<00:03, 28.66it/s][A |
|
Training...: 34%|███▍ | 48/142 [00:01<00:03, 29.82it/s][A |
|
Training...: 37%|███▋ | 52/142 [00:01<00:02, 31.16it/s][A |
|
Training...: 39%|███▉ | 56/142 [00:01<00:02, 32.08it/s][A |
|
Training...: 42%|████▏ | 60/142 [00:01<00:02, 32.86it/s][A |
|
Training...: 45%|████▌ | 64/142 [00:01<00:02, 33.56it/s][A |
|
Training...: 48%|████▊ | 68/142 [00:02<00:02, 33.50it/s][A |
|
Training...: 51%|█████ | 72/142 [00:02<00:02, 33.45it/s][A |
|
Training...: 54%|█████▎ | 76/142 [00:02<00:01, 33.40it/s][A |
|
Training...: 56%|█████▋ | 80/142 [00:02<00:01, 33.76it/s][A |
|
Training...: 59%|█████▉ | 84/142 [00:02<00:01, 34.01it/s][A |
|
Training...: 62%|██████▏ | 88/142 [00:02<00:01, 34.42it/s][A |
|
Training...: 65%|██████▍ | 92/142 [00:02<00:01, 29.32it/s][A |
|
Training...: 68%|██████▊ | 96/142 [00:02<00:01, 30.69it/s][A |
|
Training...: 70%|███████ | 100/142 [00:03<00:01, 31.87it/s][A |
|
Training...: 73%|███████▎ | 104/142 [00:03<00:01, 32.95it/s][A |
|
Training...: 76%|███████▌ | 108/142 [00:03<00:01, 33.52it/s][A |
|
Training...: 79%|███████▉ | 112/142 [00:03<00:00, 34.02it/s][A |
|
Training...: 82%|████████▏ | 116/142 [00:03<00:00, 34.45it/s][A |
|
Training...: 85%|████████▍ | 120/142 [00:03<00:00, 34.80it/s][A |
|
Training...: 87%|████████▋ | 124/142 [00:03<00:00, 35.17it/s][A |
|
Training...: 90%|█████████ | 128/142 [00:03<00:00, 35.39it/s][A |
|
Training...: 93%|█████████▎| 132/142 [00:03<00:00, 35.41it/s][A |
|
Training...: 96%|█████████▌| 136/142 [00:04<00:00, 29.58it/s][A |
|
Training...: 99%|█████████▊| 140/142 [00:04<00:00, 30.88it/s][A
Training...: 100%|██████████| 142/142 [00:04<00:00, 32.95it/s] |
|
Epoch ... (1/8): 38%|███▊ | 3/8 [01:25<01:43, 20.71s/it] |
|
Training...: 0%| | 0/142 [00:00<?, ?it/s][A |
|
Training...: 3%|▎ | 4/142 [00:00<00:04, 32.53it/s][A |
|
Training...: 6%|▌ | 8/142 [00:00<00:03, 33.90it/s][A |
|
Training...: 8%|▊ | 12/142 [00:00<00:03, 34.26it/s][A |
|
Training...: 11%|█▏ | 16/142 [00:00<00:03, 34.63it/s][A |
|
Training...: 14%|█▍ | 20/142 [00:00<00:03, 34.78it/s][A |
|
Training...: 17%|█▋ | 24/142 [00:00<00:03, 34.94it/s][A |
|
Training...: 20%|█▉ | 28/142 [00:00<00:03, 34.97it/s][A |
|
Training...: 23%|██▎ | 32/142 [00:00<00:03, 35.05it/s][A |
|
Training...: 25%|██▌ | 36/142 [00:01<00:03, 35.13it/s][A |
|
Training...: 28%|██▊ | 40/142 [00:01<00:03, 28.50it/s][A |
|
Training...: 31%|███ | 44/142 [00:01<00:03, 29.94it/s][A |
|
Training...: 34%|███▍ | 48/142 [00:01<00:03, 31.28it/s][A |
|
Training...: 37%|███▋ | 52/142 [00:01<00:02, 32.30it/s][A |
|
Training...: 39%|███▉ | 56/142 [00:01<00:02, 33.20it/s][A |
|
Training...: 42%|████▏ | 60/142 [00:01<00:02, 33.35it/s][A |
|
Training...: 45%|████▌ | 64/142 [00:01<00:02, 33.99it/s][A |
|
Training...: 48%|████▊ | 68/142 [00:02<00:02, 34.16it/s][A |
|
Training...: 51%|█████ | 72/142 [00:02<00:02, 34.41it/s][A
|
|
[A
Epoch ... (1/8): 38%|███▊ | 3/8 [01:28<01:43, 20.71s/it] |
|
Training...: 51%|█████ | 72/142 [00:02<00:02, 34.41it/s][AStep... (500 | Loss: 8.018753051757812, Learning Rate: 0.0001500000071246177) |
|
|
|
|
|
Evaluating ...: 0%| | 0/10 [00:00<?, ?it/s][A[A |
|
|
|
Evaluating ...: 10%|█ | 1/10 [00:04<00:41, 4.60s/it][A[A |
|
|
|
Evaluating ...: 90%|█████████ | 9/10 [00:04<00:00, 2.62it/s][A[A
Evaluating ...: 100%|██████████| 10/10 [00:04<00:00, 2.12it/s]huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... |
|
To disable this warning, you can either: |
|
- Avoid using `tokenizers` before the fork if possible |
|
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) |
|
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... |
|
To disable this warning, you can either: |
|
- Avoid using `tokenizers` before the fork if possible |
|
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) |
|
|
|
[16:06:12] - INFO - huggingface_hub.repository - git version 2.25.1 |
|
git-lfs/2.9.2 (GitHub; linux amd64; go 1.13.5) |
|
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... |
|
To disable this warning, you can either: |
|
- Avoid using `tokenizers` before the fork if possible |
|
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) |
|
[16:06:12] - DEBUG - huggingface_hub.repository - [Repository] is a valid git repo |
|
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... |
|
To disable this warning, you can either: |
|
- Avoid using `tokenizers` before the fork if possible |
|
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) |
|
huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks... |
|
To disable this warning, you can either: |
|
- Avoid using `tokenizers` before the fork if possible |
|
- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false) |
|
|