End of training

.ipynb_checkpoints/run-checkpoint.sh

@@ -6,7 +6,7 @@ python run_speech_recognition_ctc.py \
 --tokenizer_name_or_path="./" \
 --output_dir="./" \
 --overwrite_output_dir \
---num_train_epochs="4" \
+--num_train_epochs="1" \
 --per_device_train_batch_size="64" \
 --per_device_eval_batch_size="64" \
 --gradient_accumulation_steps="1" \
@@ -23,7 +23,7 @@ python run_speech_recognition_ctc.py \
 --save_total_limit="2" \
 --freeze_feature_encoder \
 --feat_proj_dropout="0.0" \
---mask_time_prob="0.6" \
+--mask_time_prob="0.75" \
 --mask_time_length="10" \
 --mask_feature_prob="0.25" \
 --mask_feature_length="10" \
@@ -36,6 +36,6 @@ python run_speech_recognition_ctc.py \
 --fp16 \
 --group_by_length \
 --preprocessing_num_workers="64" \
---do_train --do_eval \
+--do_train=False --do_eval \
 --load_best_model_at_end \
 --push_to_hub

.ipynb_checkpoints/run_speech_recognition_ctc-checkpoint.py

@@ -642,8 +642,7 @@ def main():
 
         pred.label_ids[pred.label_ids == -100] = tokenizer.pad_token_id
 
-        pred_str = tokenizer.batch_decode(pred_ids)#, skip_special_tokens=True)#being sure to remove <s> from the output
-        print(pred_str)
+        pred_str = tokenizer.batch_decode(pred_ids, skip_special_tokens=True)#being sure to remove <s> from the output
         # we do not want to group tokens when computing the metrics
         label_str = tokenizer.batch_decode(pred.label_ids, group_tokens=False)
 
@@ -687,7 +686,7 @@ def main():
     # 8. Finally, we can start training
 
     # Training
-    if training_args.do_train:
+    if training_args.do_train and 1 == 2:
 
         # use last checkpoint if exist
         if last_checkpoint is not None:
@@ -730,7 +729,7 @@ def main():
     kwargs = {
         "finetuned_from": model_args.model_name_or_path,
         "tasks": "speech-recognition",
-        "tags": ["automatic-speech-recognition", data_args.dataset_name],
+        "tags": ["automatic-speech-recognition", "robust-speech-event", data_args.dataset_name],
         "dataset_args": f"Config: {config_name}, Training split: {data_args.train_split_name}, Eval split: {data_args.eval_split_name}",
         "dataset": f"{data_args.dataset_name.upper()} - {config_name.upper()}",
     }

all_results.json

@@ -1,11 +1,11 @@
 {
     "epoch": 2.0,
-    "eval_loss": 21.909679412841797,
-    "eval_runtime": 271.2636,
+    "eval_loss": 0.22597630321979523,
+    "eval_runtime": 276.6037,
     "eval_samples": 4469,
-    "eval_samples_per_second": 16.475,
-    "eval_steps_per_second": 0.258,
-    "eval_wer": 1.0,
+    "eval_samples_per_second": 16.157,
+    "eval_steps_per_second": 0.253,
+    "eval_wer": 0.2948882012145466,
     "train_loss": 1.442369053426242,
     "train_runtime": 53680.5392,
     "train_samples": 442265,

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "_name_or_path": "./checkpoint-18000",
   "activation_dropout": 0.05,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -64,7 +64,7 @@
   "mask_feature_prob": 0.25,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
-  "mask_time_prob": 0.6,
+  "mask_time_prob": 0.75,
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "eval_loss": 21.909679412841797,
-    "eval_runtime": 271.2636,
+    "eval_loss": 0.22597630321979523,
+    "eval_runtime": 276.6037,
     "eval_samples": 4469,
-    "eval_samples_per_second": 16.475,
-    "eval_steps_per_second": 0.258,
-    "eval_wer": 1.0
+    "eval_samples_per_second": 16.157,
+    "eval_steps_per_second": 0.253,
+    "eval_wer": 0.2948882012145466
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6afb0187b51e7ce5d940ad3d192ccb5384c6c92b414d047431d6ebb6a0b4729b
+oid sha256:8f9c6a7fe50ee84c94a3ae149eea45203dc369fa4e7bcf46fbc4367f2385e4d3
 size 1262821553

run.sh

@@ -6,7 +6,7 @@ python run_speech_recognition_ctc.py \
 --tokenizer_name_or_path="./" \
 --output_dir="./" \
 --overwrite_output_dir \
---num_train_epochs="4" \
+--num_train_epochs="1" \
 --per_device_train_batch_size="64" \
 --per_device_eval_batch_size="64" \
 --gradient_accumulation_steps="1" \
@@ -23,19 +23,18 @@ python run_speech_recognition_ctc.py \
 --save_total_limit="2" \
 --freeze_feature_encoder \
 --feat_proj_dropout="0.0" \
---mask_time_prob="0.6" \
+--mask_time_prob="0.75" \
 --mask_time_length="10" \
 --mask_feature_prob="0.25" \
 --mask_feature_length="10" \
 --gradient_checkpointing \
 --report_to="wandb" \
 --run_name="xls-r-300m-fr" \
---max_eval_samples="4500" \
 --max_duration_in_seconds="10" \
 --use_auth_token \
 --fp16 \
 --group_by_length \
 --preprocessing_num_workers="64" \
---do_train --do_eval \
+--do_train=False --do_eval \
 --load_best_model_at_end \
 --push_to_hub

run_speech_recognition_ctc.py

@@ -686,7 +686,7 @@ def main():
     # 8. Finally, we can start training
 
     # Training
-    if training_args.do_train:
+    if training_args.do_train and 1 == 2:
 
         # use last checkpoint if exist
         if last_checkpoint is not None:

special_tokens_map.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3a67b3f8a9b2a576d3736f6fe41f32790252519745bd9adf7f9fc9090a03b0
+oid sha256:acd1210a48013d18dc58e4f6ea5c766d8c7c54f299c6e4b1a4f46aa0e01bcec9
 size 3055

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220201_103004-1yfj7vwy/logs/debug-internal.log
+run-20220201_142447-3hqii6h6/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220201_103004-1yfj7vwy/logs/debug.log
+run-20220201_142447-3hqii6h6/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220201_103004-1yfj7vwy
+run-20220201_142447-3hqii6h6

wandb/run-20220130_163246-20w0bl60/files/.ipynb_checkpoints/requirements-checkpoint.txt

@@ -0,0 +1,180 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+analytics-python==1.4.0
+anyio==3.5.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+asgiref==3.5.0
+asttokens==2.0.5
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+backcall==0.2.0
+backoff==1.10.0
+bcrypt==3.2.0
+beautifulsoup4==4.9.3
+black==21.12b0
+bleach==4.1.0
+brotlipy==0.7.0
+certifi==2020.12.5
+cffi==1.14.3
+chardet==3.0.4
+charset-normalizer==2.0.10
+click==8.0.3
+conda-build==3.21.4
+conda-package-handling==1.7.2
+conda==4.9.2
+configparser==5.2.0
+cryptography==3.2.1
+cycler==0.11.0
+datasets==1.18.2.dev0
+debugpy==1.5.1
+decorator==4.4.2
+defusedxml==0.7.1
+dill==0.3.4
+dnspython==2.1.0
+docker-pycreds==0.4.0
+entrypoints==0.3
+executing==0.8.2
+fastapi==0.73.0
+ffmpy==0.3.0
+filelock==3.0.12
+fonttools==4.29.0
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.26
+glob2==0.7
+gradio==2.7.5.2
+h11==0.13.0
+huggingface-hub==0.4.0
+idna==2.10
+importlib-resources==5.4.0
+ipykernel==6.7.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.3
+jedi==0.17.0
+jinja2==2.11.3
+jiwer==2.3.0
+joblib==1.1.0
+json5==0.9.6
+jsonschema==4.4.0
+jupyter-client==7.1.2
+jupyter-core==4.9.1
+jupyterlab-pygments==0.1.2
+jupyterlab-server==1.2.0
+jupyterlab-widgets==1.0.2
+jupyterlab==2.2.9
+kiwisolver==1.3.2
+libarchive-c==2.9
+librosa==0.8.1
+llvmlite==0.38.0
+markdown2==2.4.2
+markupsafe==1.1.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mistune==0.8.4
+mkl-fft==1.3.0
+mkl-random==1.1.1
+mkl-service==2.3.0
+monotonic==1.6
+multidict==6.0.2
+multiprocess==0.70.12.2
+mypy-extensions==0.4.3
+nano==0.10.0
+nbclient==0.5.10
+nbconvert==6.4.1
+nbformat==5.1.3
+nest-asyncio==1.5.4
+notebook==6.4.8
+numba==0.55.1
+numpy==1.19.2
+olefile==0.46
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+paramiko==2.9.2
+parso==0.8.1
+pathspec==0.9.0
+pathtools==0.1.2
+pexpect==4.8.0
+pickleshare==0.7.5
+pillow==8.1.2
+pip==21.3.1
+pkginfo==1.7.0
+platformdirs==2.4.1
+pooch==1.6.0
+prometheus-client==0.13.0
+promise==2.3
+prompt-toolkit==3.0.8
+protobuf==3.19.4
+psutil==5.8.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==6.0.1
+pycosat==0.6.3
+pycparser==2.20
+pycryptodome==3.13.0
+pydantic==1.9.0
+pydub==0.25.1
+pygments==2.8.0
+pynacl==1.5.0
+pyopenssl==19.1.0
+pyparsing==3.0.7
+pyrsistent==0.18.1
+pysocks==1.7.1
+python-dateutil==2.8.2
+python-etcd==0.4.5
+python-levenshtein==0.12.2
+python-multipart==0.0.5
+pytz==2021.1
+pyyaml==5.4.1
+pyzmq==22.3.0
+regex==2022.1.18
+requests==2.24.0
+resampy==0.2.2
+ruamel-yaml==0.15.87
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+send2trash==1.8.0
+sentry-sdk==1.5.4
+setuptools==50.3.1.post20201107
+shortuuid==1.0.8
+six==1.15.0
+smmap==5.0.0
+sniffio==1.2.0
+soundfile==0.10.3.post1
+soupsieve==2.2
+stack-data==0.1.4
+starlette==0.17.1
+subprocess32==3.5.4
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+threadpoolctl==3.0.0
+tokenizers==0.11.4
+tomli==1.2.3
+torch==1.10.2
+torchaudio==0.10.2
+torchelastic==0.2.2
+torchtext==0.9.1
+torchvision==0.9.1
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.17.0.dev0
+typing-extensions==4.0.1
+urllib3==1.25.11
+uvicorn==0.17.1
+wandb==0.12.9
+wcwidth==0.2.5
+webencodings==0.5.1
+wheel==0.35.1
+widgetsnbextension==3.5.2
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220201_103004-1yfj7vwy/files/config.yaml

@@ -45,7 +45,13 @@ _wandb:
       - 1
       - 5
       - 11
+      2:
+      - 1
+      - 5
+      - 11
       3:
+      - 1
+      - 7
       - 13
       4: 3.8.8
       5: 0.12.9

wandb/run-20220201_103004-1yfj7vwy/files/output.log

@@ -28,3 +28,8 @@ Upload file pytorch_model.bin: 100%|██████████████
 Upload file training_args.bin: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2.98k/2.98k [01:12<?, ?B/s]
 Upload file wandb/run-20220130_191954-1mtmnz5y/run-1mtmnz5y.wandb: 100%|█████████████████████████████████████████████████████████████████████| 201M/201M [01:12<00:00, 2.89MB/s]
 
+{'dataset': {'name': 'MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - FR', 'type': 'common_voice', 'args': 'Config: fr, Training split: train+validation, Eval split: test'}}00, 1.02MB/s]
+02/01/2022 10:32:47 - WARNING - huggingface_hub.repository - To https://huggingface.co/AlexN/xls-r-300m-fr
+   f25a924..a37375f  main -> main
+To https://huggingface.co/AlexN/xls-r-300m-fr
+   f25a924..a37375f  main -> main

wandb/run-20220201_103004-1yfj7vwy/files/wandb-summary.json

@@ -1 +1 @@
-{"eval/loss": 21.909679412841797, "eval/wer": 1.0, "eval/runtime": 271.2636, "eval/samples_per_second": 16.475, "eval/steps_per_second": 0.258, "train/global_step": 0, "_runtime": 2, "_timestamp": 1643711406, "_step": 0}
+{"eval/loss": 21.909679412841797, "eval/wer": 1.0, "eval/runtime": 271.2636, "eval/samples_per_second": 16.475, "eval/steps_per_second": 0.258, "train/global_step": 0, "_runtime": 2, "_timestamp": 1643711406, "_step": 0, "_wandb": {"runtime": 167}}

wandb/run-20220201_103004-1yfj7vwy/logs/debug-internal.log

@@ -78,3 +78,115 @@
 2022-02-01 10:32:38,165 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: stop_status
 2022-02-01 10:32:42,989 INFO    Thread-8  :61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/output.log
 2022-02-01 10:32:44,990 INFO    Thread-8  :61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/output.log
+2022-02-01 10:32:48,993 INFO    Thread-8  :61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/output.log
+2022-02-01 10:32:52,987 DEBUG   SenderThread:61045 [sender.py:send():234] send: telemetry
+2022-02-01 10:32:52,988 DEBUG   SenderThread:61045 [sender.py:send():234] send: exit
+2022-02-01 10:32:52,988 INFO    SenderThread:61045 [sender.py:send_exit():366] handling exit code: 0
+2022-02-01 10:32:52,988 INFO    SenderThread:61045 [sender.py:send_exit():368] handling runtime: 167
+2022-02-01 10:32:52,989 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:52,990 INFO    SenderThread:61045 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
+2022-02-01 10:32:52,990 INFO    SenderThread:61045 [sender.py:send_exit():374] send defer
+2022-02-01 10:32:52,990 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:52,991 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:52,992 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 0
+2022-02-01 10:32:52,992 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:52,992 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 0
+2022-02-01 10:32:52,992 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 1
+2022-02-01 10:32:52,993 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:52,993 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 1
+2022-02-01 10:32:52,996 INFO    Thread-8  :61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/output.log
+2022-02-01 10:32:52,996 INFO    Thread-8  :61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/wandb-summary.json
+2022-02-01 10:32:53,088 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:53,088 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 1
+2022-02-01 10:32:53,088 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 2
+2022-02-01 10:32:53,088 DEBUG   SenderThread:61045 [sender.py:send():234] send: stats
+2022-02-01 10:32:53,089 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:53,089 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 2
+2022-02-01 10:32:53,090 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:53,090 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 2
+2022-02-01 10:32:53,090 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 3
+2022-02-01 10:32:53,090 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:53,090 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 3
+2022-02-01 10:32:53,091 DEBUG   SenderThread:61045 [sender.py:send():234] send: summary
+2022-02-01 10:32:53,092 INFO    SenderThread:61045 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
+2022-02-01 10:32:53,092 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:53,092 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 3
+2022-02-01 10:32:53,092 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 4
+2022-02-01 10:32:53,093 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:53,093 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 4
+2022-02-01 10:32:53,093 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:53,093 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 4
+2022-02-01 10:32:53,103 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:53,344 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 5
+2022-02-01 10:32:53,344 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:53,345 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:53,345 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 5
+2022-02-01 10:32:53,345 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:53,345 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 5
+2022-02-01 10:32:53,345 INFO    SenderThread:61045 [dir_watcher.py:finish():283] shutting down directory watcher
+2022-02-01 10:32:53,448 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:53,997 INFO    Thread-8  :61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/config.yaml
+2022-02-01 10:32:53,998 INFO    SenderThread:61045 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/wandb-summary.json
+2022-02-01 10:32:53,999 INFO    SenderThread:61045 [dir_watcher.py:finish():313] scan: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files
+2022-02-01 10:32:53,999 INFO    SenderThread:61045 [dir_watcher.py:finish():327] scan save: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/output.log output.log
+2022-02-01 10:32:54,000 INFO    SenderThread:61045 [dir_watcher.py:finish():327] scan save: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/wandb-metadata.json wandb-metadata.json
+2022-02-01 10:32:54,001 INFO    SenderThread:61045 [dir_watcher.py:finish():327] scan save: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/config.yaml config.yaml
+2022-02-01 10:32:54,007 INFO    SenderThread:61045 [dir_watcher.py:finish():327] scan save: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/conda-environment.yaml conda-environment.yaml
+2022-02-01 10:32:54,014 INFO    SenderThread:61045 [dir_watcher.py:finish():327] scan save: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/wandb-summary.json wandb-summary.json
+2022-02-01 10:32:54,015 INFO    SenderThread:61045 [dir_watcher.py:finish():327] scan save: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/requirements.txt requirements.txt
+2022-02-01 10:32:54,019 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 6
+2022-02-01 10:32:54,020 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,026 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:54,026 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 6
+2022-02-01 10:32:54,026 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:54,027 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 6
+2022-02-01 10:32:54,027 INFO    SenderThread:61045 [file_pusher.py:finish():177] shutting down file pusher
+2022-02-01 10:32:54,122 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,123 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,225 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,226 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,328 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,329 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,431 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,432 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,524 INFO    Thread-14 :61045 [upload_job.py:push():137] Uploaded file /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/wandb-summary.json
+2022-02-01 10:32:54,531 INFO    Thread-12 :61045 [upload_job.py:push():137] Uploaded file /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/output.log
+2022-02-01 10:32:54,534 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,534 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,542 INFO    Thread-15 :61045 [upload_job.py:push():137] Uploaded file /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/requirements.txt
+2022-02-01 10:32:54,556 INFO    Thread-13 :61045 [upload_job.py:push():137] Uploaded file /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/files/config.yaml
+2022-02-01 10:32:54,636 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,637 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,739 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:54,739 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:54,757 INFO    Thread-7  :61045 [sender.py:transition_state():387] send defer: 7
+2022-02-01 10:32:54,758 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:54,759 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 7
+2022-02-01 10:32:54,759 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:54,759 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 7
+2022-02-01 10:32:54,842 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:55,205 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 8
+2022-02-01 10:32:55,206 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:55,206 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:55,207 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 8
+2022-02-01 10:32:55,208 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:55,208 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 8
+2022-02-01 10:32:55,208 INFO    SenderThread:61045 [sender.py:transition_state():387] send defer: 9
+2022-02-01 10:32:55,209 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: defer
+2022-02-01 10:32:55,210 INFO    HandlerThread:61045 [handler.py:handle_request_defer():147] handle defer: 9
+2022-02-01 10:32:55,210 DEBUG   SenderThread:61045 [sender.py:send():234] send: final
+2022-02-01 10:32:55,210 DEBUG   SenderThread:61045 [sender.py:send():234] send: footer
+2022-02-01 10:32:55,210 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: defer
+2022-02-01 10:32:55,210 INFO    SenderThread:61045 [sender.py:send_request_defer():383] handle sender defer: 9
+2022-02-01 10:32:55,309 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: poll_exit
+2022-02-01 10:32:55,310 DEBUG   SenderThread:61045 [sender.py:send_request():248] send_request: poll_exit
+2022-02-01 10:32:55,310 INFO    SenderThread:61045 [file_pusher.py:join():182] waiting for file pusher
+2022-02-01 10:32:55,613 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: get_summary
+2022-02-01 10:32:55,615 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: sampled_history
+2022-02-01 10:32:55,617 DEBUG   HandlerThread:61045 [handler.py:handle_request():130] handle_request: shutdown
+2022-02-01 10:32:55,617 INFO    HandlerThread:61045 [handler.py:finish():731] shutting down handler
+2022-02-01 10:32:56,210 INFO    WriterThread:61045 [datastore.py:close():281] close: /workspace/xls-r-300m-fr/wandb/run-20220201_103004-1yfj7vwy/run-1yfj7vwy.wandb
+2022-02-01 10:32:56,611 INFO    SenderThread:61045 [sender.py:finish():1070] shutting down sender
+2022-02-01 10:32:56,611 INFO    SenderThread:61045 [file_pusher.py:finish():177] shutting down file pusher
+2022-02-01 10:32:56,611 INFO    SenderThread:61045 [file_pusher.py:join():182] waiting for file pusher
+2022-02-01 10:32:56,615 INFO    MainThread:61045 [internal.py:handle_exit():77] Internal process exited

wandb/run-20220201_103004-1yfj7vwy/logs/debug.log

@@ -22,3 +22,109 @@ config: {}
 2022-02-01 10:30:06,517 INFO    MainThread:58652 [wandb_init.py:init():633] run started, returning control to user process
 2022-02-01 10:30:06,519 INFO    MainThread:58652 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 218, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-xls-r-300m', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.05, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 219, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.6, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.25, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 64, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 2700, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Feb01_10-24-12_job-1abccd0a-3293-4ffe-8274-9e8f841f653f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'xls-r-300m-fr', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'train_batch_size': 64, 'eval_batch_size': 64}
 2022-02-01 10:30:06,524 INFO    MainThread:58652 [wandb_watch.py:watch():43] Watching
+2022-02-01 10:32:50,469 INFO    MainThread:58652 [wandb_run.py:_atexit_cleanup():1780] got exitcode: 0
+2022-02-01 10:32:50,473 INFO    MainThread:58652 [wandb_run.py:_restore():1752] restore
+2022-02-01 10:32:52,992 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2158
+  total_bytes: 2158
+}
+
+2022-02-01 10:32:53,346 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2158
+  total_bytes: 2158
+}
+
+2022-02-01 10:32:54,021 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2158
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,124 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2158
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,227 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2158
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,330 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,432 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,535 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,637 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:54,740 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:55,208 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+
+2022-02-01 10:32:55,612 INFO    MainThread:58652 [wandb_run.py:_wait_for_finish():1912] got exit ret: done: true
+exit_result {
+}
+file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 18907
+  total_bytes: 18907
+}
+local_info {
+}
+
+2022-02-01 10:32:56,753 INFO    MainThread:58652 [wandb_run.py:_append_history():2130] rendering history
+2022-02-01 10:32:56,754 INFO    MainThread:58652 [wandb_run.py:_append_summary():2085] rendering summary
+2022-02-01 10:32:56,754 INFO    MainThread:58652 [wandb_run.py:_append_files():2180] logging synced files

wandb/run-20220201_115151-3ujx6xdv/files/output.log

@@ -0,0 +1,243 @@
+
+  0%|                                                                                                                                                 | 0/27860 [00:00<?, ?it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|███████████████████████████████████████████████████████████████████████████████████▏                                            | 18100/27860 [2:16:21<10:06:40,  3.73s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 65%|███████████████████████████████████████████████████████████████████████████████████▌                                            | 18200/27860 [2:22:00<10:24:13,  3.88s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  File "run_speech_recognition_ctc.py", line 748, in <module>████████████████████████████▍                                            | 18230/27860 [2:23:19<4:36:39,  1.72s/it]
+    main()
+  File "run_speech_recognition_ctc.py", line 699, in main
+    train_result = trainer.train(resume_from_checkpoint=checkpoint)
+  File "/opt/conda/lib/python3.8/site-packages/transformers/trainer.py", line 1373, in train
+    tr_loss_step = self.training_step(model, inputs)
+  File "/opt/conda/lib/python3.8/site-packages/transformers/trainer.py", line 1948, in training_step
+    loss = self.compute_loss(model, inputs)
+  File "/opt/conda/lib/python3.8/site-packages/transformers/trainer.py", line 1980, in compute_loss
+    outputs = model(**inputs)
+  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
+    return forward_call(*input, **kwargs)
+  File "/opt/conda/lib/python3.8/site-packages/transformers/models/wav2vec2/modeling_wav2vec2.py", line 1758, in forward
+    if labels.max() >= self.config.vocab_size:
+KeyboardInterrupt

wandb/run-20220201_115151-3ujx6xdv/files/requirements.txt

@@ -0,0 +1,180 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+analytics-python==1.4.0
+anyio==3.5.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+asgiref==3.5.0
+asttokens==2.0.5
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+backcall==0.2.0
+backoff==1.10.0
+bcrypt==3.2.0
+beautifulsoup4==4.9.3
+black==21.12b0
+bleach==4.1.0
+brotlipy==0.7.0
+certifi==2020.12.5
+cffi==1.14.3
+chardet==3.0.4
+charset-normalizer==2.0.10
+click==8.0.3
+conda-build==3.21.4
+conda-package-handling==1.7.2
+conda==4.9.2
+configparser==5.2.0
+cryptography==3.2.1
+cycler==0.11.0
+datasets==1.18.2.dev0
+debugpy==1.5.1
+decorator==4.4.2
+defusedxml==0.7.1
+dill==0.3.4
+dnspython==2.1.0
+docker-pycreds==0.4.0
+entrypoints==0.3
+executing==0.8.2
+fastapi==0.73.0
+ffmpy==0.3.0
+filelock==3.0.12
+fonttools==4.29.0
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.26
+glob2==0.7
+gradio==2.7.5.2
+h11==0.13.0
+huggingface-hub==0.4.0
+idna==2.10
+importlib-resources==5.4.0
+ipykernel==6.7.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.3
+jedi==0.17.0
+jinja2==2.11.3
+jiwer==2.3.0
+joblib==1.1.0
+json5==0.9.6
+jsonschema==4.4.0
+jupyter-client==7.1.2
+jupyter-core==4.9.1
+jupyterlab-pygments==0.1.2
+jupyterlab-server==1.2.0
+jupyterlab-widgets==1.0.2
+jupyterlab==2.2.9
+kiwisolver==1.3.2
+libarchive-c==2.9
+librosa==0.8.1
+llvmlite==0.38.0
+markdown2==2.4.2
+markupsafe==1.1.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mistune==0.8.4
+mkl-fft==1.3.0
+mkl-random==1.1.1
+mkl-service==2.3.0
+monotonic==1.6
+multidict==6.0.2
+multiprocess==0.70.12.2
+mypy-extensions==0.4.3
+nano==0.10.0
+nbclient==0.5.10
+nbconvert==6.4.1
+nbformat==5.1.3
+nest-asyncio==1.5.4
+notebook==6.4.8
+numba==0.55.1
+numpy==1.19.2
+olefile==0.46
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+paramiko==2.9.2
+parso==0.8.1
+pathspec==0.9.0
+pathtools==0.1.2
+pexpect==4.8.0
+pickleshare==0.7.5
+pillow==8.1.2
+pip==21.3.1
+pkginfo==1.7.0
+platformdirs==2.4.1
+pooch==1.6.0
+prometheus-client==0.13.0
+promise==2.3
+prompt-toolkit==3.0.8
+protobuf==3.19.4
+psutil==5.8.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==6.0.1
+pycosat==0.6.3
+pycparser==2.20
+pycryptodome==3.13.0
+pydantic==1.9.0
+pydub==0.25.1
+pygments==2.8.0
+pynacl==1.5.0
+pyopenssl==19.1.0
+pyparsing==3.0.7
+pyrsistent==0.18.1
+pysocks==1.7.1
+python-dateutil==2.8.2
+python-etcd==0.4.5
+python-levenshtein==0.12.2
+python-multipart==0.0.5
+pytz==2021.1
+pyyaml==5.4.1
+pyzmq==22.3.0
+regex==2022.1.18
+requests==2.24.0
+resampy==0.2.2
+ruamel-yaml==0.15.87
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+send2trash==1.8.0
+sentry-sdk==1.5.4
+setuptools==50.3.1.post20201107
+shortuuid==1.0.8
+six==1.15.0
+smmap==5.0.0
+sniffio==1.2.0
+soundfile==0.10.3.post1
+soupsieve==2.2
+stack-data==0.1.4
+starlette==0.17.1
+subprocess32==3.5.4
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+threadpoolctl==3.0.0
+tokenizers==0.11.4
+tomli==1.2.3
+torch==1.10.2
+torchaudio==0.10.2
+torchelastic==0.2.2
+torchtext==0.9.1
+torchvision==0.9.1
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.17.0.dev0
+typing-extensions==4.0.1
+urllib3==1.25.11
+uvicorn==0.17.1
+wandb==0.12.9
+wcwidth==0.2.5
+webencodings==0.5.1
+wheel==0.35.1
+widgetsnbextension==3.5.2
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220201_115151-3ujx6xdv/files/wandb-metadata.json

@@ -0,0 +1,65 @@
+{
+    "os": "Linux-4.15.0-151-generic-x86_64-with-glibc2.10",
+    "python": "3.8.8",
+    "heartbeatAt": "2022-02-01T11:51:53.049589",
+    "startedAt": "2022-02-01T11:51:51.626030",
+    "docker": null,
+    "gpu": "Tesla V100S-PCIE-32GB",
+    "gpu_count": 1,
+    "cpu_count": 60,
+    "cuda": null,
+    "args": [
+        "--dataset_name=mozilla-foundation/common_voice_8_0",
+        "--model_name_or_path=./checkpoint-18000",
+        "--dataset_config_name=fr",
+        "--tokenizer_name_or_path=./",
+        "--output_dir=./",
+        "--overwrite_output_dir",
+        "--num_train_epochs=4",
+        "--per_device_train_batch_size=64",
+        "--per_device_eval_batch_size=64",
+        "--gradient_accumulation_steps=1",
+        "--learning_rate=1e-4",
+        "--warmup_steps=2700",
+        "--length_column_name=input_length",
+        "--evaluation_strategy=steps",
+        "--text_column_name=sentence",
+        "--save_steps=500",
+        "--eval_steps=500",
+        "--logging_steps=100",
+        "--layerdrop=0.0",
+        "--activation_dropout=0.05",
+        "--save_total_limit=2",
+        "--freeze_feature_encoder",
+        "--feat_proj_dropout=0.0",
+        "--mask_time_prob=0.6",
+        "--mask_time_length=10",
+        "--mask_feature_prob=0.25",
+        "--mask_feature_length=10",
+        "--gradient_checkpointing",
+        "--report_to=wandb",
+        "--run_name=xls-r-300m-fr",
+        "--max_eval_samples=4500",
+        "--max_duration_in_seconds=10",
+        "--use_auth_token",
+        "--fp16",
+        "--group_by_length",
+        "--preprocessing_num_workers=64",
+        "--do_train",
+        "--do_eval",
+        "--load_best_model_at_end",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "run_speech_recognition_ctc.py",
+    "codePath": "run_speech_recognition_ctc.py",
+    "git": {
+        "remote": "https://huggingface.co/AlexN/xls-r-300m-fr",
+        "commit": "a37375f05121cad39aba4409ef22f6f71610efc6"
+    },
+    "email": "alexandrenap@hotmail.fr",
+    "root": "/workspace/xls-r-300m-fr",
+    "host": "job-1abccd0a-3293-4ffe-8274-9e8f841f653f",
+    "username": "ovh",
+    "executable": "/opt/conda/bin/python"
+}

wandb/run-20220201_115151-3ujx6xdv/logs/debug.log

@@ -0,0 +1,162 @@
+2022-02-01 11:51:51,630 INFO    MainThread:1674 [wandb_setup.py:_flush():71] setting env: {}
+2022-02-01 11:51:51,630 INFO    MainThread:1674 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-02-01 11:51:51,630 INFO    MainThread:1674 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-fr/wandb/run-20220201_115151-3ujx6xdv/logs/debug.log
+2022-02-01 11:51:51,630 INFO    MainThread:1674 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-fr/wandb/run-20220201_115151-3ujx6xdv/logs/debug-internal.log
+2022-02-01 11:51:51,631 INFO    MainThread:1674 [wandb_init.py:init():404] calling init triggers
+2022-02-01 11:51:51,631 INFO    MainThread:1674 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-02-01 11:51:51,631 INFO    MainThread:1674 [wandb_init.py:init():460] starting backend
+2022-02-01 11:51:51,631 INFO    MainThread:1674 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-02-01 11:51:51,727 INFO    MainThread:1674 [backend.py:ensure_launched():216] starting backend process...
+2022-02-01 11:51:51,860 INFO    MainThread:1674 [backend.py:ensure_launched():221] started backend process with pid: 32352
+2022-02-01 11:51:51,865 INFO    MainThread:1674 [wandb_init.py:init():469] backend started and connected
+2022-02-01 11:51:51,874 INFO    MainThread:1674 [wandb_init.py:init():533] updated telemetry
+2022-02-01 11:51:52,115 INFO    MainThread:1674 [wandb_init.py:init():563] communicating current version
+2022-02-01 11:51:52,852 INFO    MainThread:1674 [wandb_init.py:init():568] got version response 
+2022-02-01 11:51:52,852 INFO    MainThread:1674 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-02-01 11:51:53,041 INFO    MainThread:1674 [wandb_init.py:init():606] starting run threads in backend
+2022-02-01 11:51:53,693 INFO    MainThread:1674 [wandb_run.py:_console_start():1810] atexit reg
+2022-02-01 11:51:53,694 INFO    MainThread:1674 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-02-01 11:51:53,695 INFO    MainThread:1674 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-02-01 11:51:53,701 INFO    MainThread:1674 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-02-01 11:51:53,701 INFO    MainThread:1674 [wandb_init.py:init():633] run started, returning control to user process
+2022-02-01 11:51:53,703 INFO    MainThread:1674 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForCTC'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 218, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './checkpoint-18000', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.05, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 219, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.6, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.25, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 64, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 4.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 2700, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Feb01_10-33-03_job-1abccd0a-3293-4ffe-8274-9e8f841f653f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'xls-r-300m-fr', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'train_batch_size': 64, 'eval_batch_size': 64}
+2022-02-01 11:51:53,707 INFO    MainThread:1674 [wandb_watch.py:watch():43] Watching
+2022-02-01 14:15:18,365 INFO    MainThread:1674 [wandb_run.py:_atexit_cleanup():1780] got exitcode: 255
+2022-02-01 14:15:18,367 INFO    MainThread:1674 [wandb_run.py:_restore():1752] restore
+2022-02-01 14:15:20,545 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2170
+  total_bytes: 2170
+}
+
+2022-02-01 14:15:20,670 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2170
+  total_bytes: 2170
+}
+
+2022-02-01 14:15:21,400 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 2170
+  total_bytes: 2170
+}
+
+2022-02-01 14:15:21,882 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 4
+}
+pusher_stats {
+  uploaded_bytes: 2170
+  total_bytes: 875506
+}
+
+2022-02-01 14:15:21,985 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2170
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,092 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 2170
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,196 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,299 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,401 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,504 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,606 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,709 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,812 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:22,915 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:24,234 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+
+2022-02-01 14:15:24,652 INFO    MainThread:1674 [wandb_run.py:_wait_for_finish():1912] got exit ret: done: true
+exit_result {
+}
+file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 878639
+  total_bytes: 878639
+}
+local_info {
+}
+
+2022-02-01 14:15:25,813 INFO    MainThread:1674 [wandb_run.py:_append_history():2130] rendering history
+2022-02-01 14:15:25,813 INFO    MainThread:1674 [wandb_run.py:_append_summary():2085] rendering summary
+2022-02-01 14:15:25,814 INFO    MainThread:1674 [wandb_run.py:_append_files():2180] logging synced files

wandb/run-20220201_142447-3hqii6h6/files/config.yaml

@@ -0,0 +1,668 @@
+wandb_version: 1
+
+_n_gpu:
+  desc: null
+  value: 1
+_name_or_path:
+  desc: null
+  value: ./checkpoint-18000
+_wandb:
+  desc: null
+  value:
+    cli_version: 0.12.9
+    framework: huggingface
+    huggingface_version: 4.17.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: eval/loss
+      5: 1
+      6:
+      - 1
+    - 1: eval/wer
+      5: 1
+      6:
+      - 1
+    - 1: eval/runtime
+      5: 1
+      6:
+      - 1
+    - 1: eval/samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: eval/steps_per_second
+      5: 1
+      6:
+      - 1
+    python_version: 3.8.8
+    start_time: 1643725488
+    t:
+      1:
+      - 1
+      - 5
+      - 11
+      3:
+      - 13
+      4: 3.8.8
+      5: 0.12.9
+      6: 4.17.0.dev0
+      8:
+      - 5
+activation_dropout:
+  desc: null
+  value: 0.05
+adafactor:
+  desc: null
+  value: false
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+adapter_kernel_size:
+  desc: null
+  value: 3
+adapter_stride:
+  desc: null
+  value: 2
+add_adapter:
+  desc: null
+  value: false
+add_cross_attention:
+  desc: null
+  value: false
+apply_spec_augment:
+  desc: null
+  value: true
+architectures:
+  desc: null
+  value:
+  - Wav2Vec2ForCTC
+attention_dropout:
+  desc: null
+  value: 0.0
+bad_words_ids:
+  desc: null
+  value: null
+bf16:
+  desc: null
+  value: false
+bf16_full_eval:
+  desc: null
+  value: false
+bos_token_id:
+  desc: null
+  value: 1
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+classifier_proj_size:
+  desc: null
+  value: 256
+codevector_dim:
+  desc: null
+  value: 768
+contrastive_logits_temperature:
+  desc: null
+  value: 0.1
+conv_bias:
+  desc: null
+  value: true
+conv_dim:
+  desc: null
+  value:
+  - 512
+  - 512
+  - 512
+  - 512
+  - 512
+  - 512
+  - 512
+conv_kernel:
+  desc: null
+  value:
+  - 10
+  - 3
+  - 3
+  - 3
+  - 3
+  - 2
+  - 2
+conv_stride:
+  desc: null
+  value:
+  - 5
+  - 2
+  - 2
+  - 2
+  - 2
+  - 2
+  - 2
+cross_attention_hidden_size:
+  desc: null
+  value: null
+ctc_loss_reduction:
+  desc: null
+  value: mean
+ctc_zero_infinity:
+  desc: null
+  value: false
+dataloader_drop_last:
+  desc: null
+  value: false
+dataloader_num_workers:
+  desc: null
+  value: 0
+dataloader_pin_memory:
+  desc: null
+  value: true
+ddp_bucket_cap_mb:
+  desc: null
+  value: None
+ddp_find_unused_parameters:
+  desc: null
+  value: None
+debug:
+  desc: null
+  value: '[]'
+decoder_start_token_id:
+  desc: null
+  value: null
+deepspeed:
+  desc: null
+  value: None
+disable_tqdm:
+  desc: null
+  value: false
+diversity_loss_weight:
+  desc: null
+  value: 0.1
+diversity_penalty:
+  desc: null
+  value: 0.0
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+do_sample:
+  desc: null
+  value: false
+do_stable_layer_norm:
+  desc: null
+  value: true
+do_train:
+  desc: null
+  value: false
+early_stopping:
+  desc: null
+  value: false
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: None
+eval_batch_size:
+  desc: null
+  value: 64
+eval_steps:
+  desc: null
+  value: 500
+evaluation_strategy:
+  desc: null
+  value: steps
+feat_extract_activation:
+  desc: null
+  value: gelu
+feat_extract_dropout:
+  desc: null
+  value: 0.0
+feat_extract_norm:
+  desc: null
+  value: layer
+feat_proj_dropout:
+  desc: null
+  value: 0.0
+feat_quantizer_dropout:
+  desc: null
+  value: 0.0
+final_dropout:
+  desc: null
+  value: 0.0
+finetuning_task:
+  desc: null
+  value: null
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+fp16:
+  desc: null
+  value: true
+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
+gradient_checkpointing:
+  desc: null
+  value: true
+greater_is_better:
+  desc: null
+  value: false
+group_by_length:
+  desc: null
+  value: true
+half_precision_backend:
+  desc: null
+  value: amp
+hidden_act:
+  desc: null
+  value: gelu
+hidden_dropout:
+  desc: null
+  value: 0.0
+hidden_size:
+  desc: null
+  value: 1024
+hub_model_id:
+  desc: null
+  value: None
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+ignore_data_skip:
+  desc: null
+  value: false
+initializer_range:
+  desc: null
+  value: 0.02
+intermediate_size:
+  desc: null
+  value: 4096
+is_decoder:
+  desc: null
+  value: false
+is_encoder_decoder:
+  desc: null
+  value: false
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+label_names:
+  desc: null
+  value: None
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+layer_norm_eps:
+  desc: null
+  value: 1.0e-05
+layerdrop:
+  desc: null
+  value: 0.0
+learning_rate:
+  desc: null
+  value: 0.0001
+length_column_name:
+  desc: null
+  value: input_length
+length_penalty:
+  desc: null
+  value: 1.0
+load_best_model_at_end:
+  desc: null
+  value: true
+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/Feb01_14-18-51_job-1abccd0a-3293-4ffe-8274-9e8f841f653f
+logging_first_step:
+  desc: null
+  value: false
+logging_nan_inf_filter:
+  desc: null
+  value: true
+logging_steps:
+  desc: null
+  value: 100
+logging_strategy:
+  desc: null
+  value: steps
+lr_scheduler_type:
+  desc: null
+  value: linear
+mask_feature_length:
+  desc: null
+  value: 10
+mask_feature_min_masks:
+  desc: null
+  value: 0
+mask_feature_prob:
+  desc: null
+  value: 0.25
+mask_time_length:
+  desc: null
+  value: 10
+mask_time_min_masks:
+  desc: null
+  value: 2
+mask_time_prob:
+  desc: null
+  value: 0.75
+max_grad_norm:
+  desc: null
+  value: 1.0
+max_length:
+  desc: null
+  value: 20
+max_steps:
+  desc: null
+  value: -1
+metric_for_best_model:
+  desc: null
+  value: loss
+min_length:
+  desc: null
+  value: 0
+model_type:
+  desc: null
+  value: wav2vec2
+mp_parameters:
+  desc: null
+  value: ''
+no_cuda:
+  desc: null
+  value: false
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+num_adapter_layers:
+  desc: null
+  value: 3
+num_attention_heads:
+  desc: null
+  value: 16
+num_beam_groups:
+  desc: null
+  value: 1
+num_beams:
+  desc: null
+  value: 1
+num_codevector_groups:
+  desc: null
+  value: 2
+num_codevectors_per_group:
+  desc: null
+  value: 320
+num_conv_pos_embedding_groups:
+  desc: null
+  value: 16
+num_conv_pos_embeddings:
+  desc: null
+  value: 128
+num_feat_extract_layers:
+  desc: null
+  value: 7
+num_hidden_layers:
+  desc: null
+  value: 24
+num_negatives:
+  desc: null
+  value: 100
+num_return_sequences:
+  desc: null
+  value: 1
+num_train_epochs:
+  desc: null
+  value: 1.0
+optim:
+  desc: null
+  value: adamw_hf
+output_attentions:
+  desc: null
+  value: false
+output_dir:
+  desc: null
+  value: ./
+output_hidden_size:
+  desc: null
+  value: 1024
+output_hidden_states:
+  desc: null
+  value: false
+output_scores:
+  desc: null
+  value: false
+overwrite_output_dir:
+  desc: null
+  value: true
+pad_token_id:
+  desc: null
+  value: 218
+past_index:
+  desc: null
+  value: -1
+per_device_eval_batch_size:
+  desc: null
+  value: 64
+per_device_train_batch_size:
+  desc: null
+  value: 64
+per_gpu_eval_batch_size:
+  desc: null
+  value: None
+per_gpu_train_batch_size:
+  desc: null
+  value: None
+prediction_loss_only:
+  desc: null
+  value: false
+prefix:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+proj_codevector_dim:
+  desc: null
+  value: 768
+pruned_heads:
+  desc: null
+  value: {}
+push_to_hub:
+  desc: null
+  value: true
+push_to_hub_model_id:
+  desc: null
+  value: None
+push_to_hub_organization:
+  desc: null
+  value: None
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+remove_invalid_values:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+repetition_penalty:
+  desc: null
+  value: 1.0
+report_to:
+  desc: null
+  value: '[''wandb'']'
+resume_from_checkpoint:
+  desc: null
+  value: None
+return_dict:
+  desc: null
+  value: true
+return_dict_in_generate:
+  desc: null
+  value: false
+run_name:
+  desc: null
+  value: xls-r-300m-fr
+save_on_each_node:
+  desc: null
+  value: false
+save_steps:
+  desc: null
+  value: 500
+save_strategy:
+  desc: null
+  value: steps
+save_total_limit:
+  desc: null
+  value: 2
+seed:
+  desc: null
+  value: 42
+sep_token_id:
+  desc: null
+  value: null
+sharded_ddp:
+  desc: null
+  value: '[]'
+skip_memory_metrics:
+  desc: null
+  value: true
+task_specific_params:
+  desc: null
+  value: null
+tdnn_dilation:
+  desc: null
+  value:
+  - 1
+  - 2
+  - 3
+  - 1
+  - 1
+tdnn_dim:
+  desc: null
+  value:
+  - 512
+  - 512
+  - 512
+  - 512
+  - 1500
+tdnn_kernel:
+  desc: null
+  value:
+  - 5
+  - 3
+  - 3
+  - 1
+  - 1
+temperature:
+  desc: null
+  value: 1.0
+tf32:
+  desc: null
+  value: None
+tie_encoder_decoder:
+  desc: null
+  value: false
+tie_word_embeddings:
+  desc: null
+  value: true
+tokenizer_class:
+  desc: null
+  value: null
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+torch_dtype:
+  desc: null
+  value: float32
+torchscript:
+  desc: null
+  value: false
+tpu_metrics_debug:
+  desc: null
+  value: false
+tpu_num_cores:
+  desc: null
+  value: None
+train_batch_size:
+  desc: null
+  value: 64
+transformers_version:
+  desc: null
+  value: 4.17.0.dev0
+use_bfloat16:
+  desc: null
+  value: false
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+use_weighted_layer_sum:
+  desc: null
+  value: false
+vocab_size:
+  desc: null
+  value: 219
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 2700
+weight_decay:
+  desc: null
+  value: 0.0
+xpu_backend:
+  desc: null
+  value: None
+xvector_output_dim:
+  desc: null
+  value: 512

wandb/run-20220201_142447-3hqii6h6/files/output.log

@@ -0,0 +1,11 @@
+***** eval metrics *****
+  eval_loss               =      0.226
+  eval_runtime            = 0:04:36.60
+  eval_samples            =       4469
+  eval_samples_per_second =     16.157
+  eval_steps_per_second   =      0.253
+  eval_wer                =     0.2949
+100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 70/70 [04:36<00:00,  3.95s/it]
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+Model weights saved in ./pytorch_model.bin

wandb/run-20220201_142447-3hqii6h6/files/requirements.txt

@@ -0,0 +1,180 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+analytics-python==1.4.0
+anyio==3.5.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+asgiref==3.5.0
+asttokens==2.0.5
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+backcall==0.2.0
+backoff==1.10.0
+bcrypt==3.2.0
+beautifulsoup4==4.9.3
+black==21.12b0
+bleach==4.1.0
+brotlipy==0.7.0
+certifi==2020.12.5
+cffi==1.14.3
+chardet==3.0.4
+charset-normalizer==2.0.10
+click==8.0.3
+conda-build==3.21.4
+conda-package-handling==1.7.2
+conda==4.9.2
+configparser==5.2.0
+cryptography==3.2.1
+cycler==0.11.0
+datasets==1.18.2.dev0
+debugpy==1.5.1
+decorator==4.4.2
+defusedxml==0.7.1
+dill==0.3.4
+dnspython==2.1.0
+docker-pycreds==0.4.0
+entrypoints==0.3
+executing==0.8.2
+fastapi==0.73.0
+ffmpy==0.3.0
+filelock==3.0.12
+fonttools==4.29.0
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.26
+glob2==0.7
+gradio==2.7.5.2
+h11==0.13.0
+huggingface-hub==0.4.0
+idna==2.10
+importlib-resources==5.4.0
+ipykernel==6.7.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.3
+jedi==0.17.0
+jinja2==2.11.3
+jiwer==2.3.0
+joblib==1.1.0
+json5==0.9.6
+jsonschema==4.4.0
+jupyter-client==7.1.2
+jupyter-core==4.9.1
+jupyterlab-pygments==0.1.2
+jupyterlab-server==1.2.0
+jupyterlab-widgets==1.0.2
+jupyterlab==2.2.9
+kiwisolver==1.3.2
+libarchive-c==2.9
+librosa==0.8.1
+llvmlite==0.38.0
+markdown2==2.4.2
+markupsafe==1.1.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mistune==0.8.4
+mkl-fft==1.3.0
+mkl-random==1.1.1
+mkl-service==2.3.0
+monotonic==1.6
+multidict==6.0.2
+multiprocess==0.70.12.2
+mypy-extensions==0.4.3
+nano==0.10.0
+nbclient==0.5.10
+nbconvert==6.4.1
+nbformat==5.1.3
+nest-asyncio==1.5.4
+notebook==6.4.8
+numba==0.55.1
+numpy==1.19.2
+olefile==0.46
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+paramiko==2.9.2
+parso==0.8.1
+pathspec==0.9.0
+pathtools==0.1.2
+pexpect==4.8.0
+pickleshare==0.7.5
+pillow==8.1.2
+pip==21.3.1
+pkginfo==1.7.0
+platformdirs==2.4.1
+pooch==1.6.0
+prometheus-client==0.13.0
+promise==2.3
+prompt-toolkit==3.0.8
+protobuf==3.19.4
+psutil==5.8.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==6.0.1
+pycosat==0.6.3
+pycparser==2.20
+pycryptodome==3.13.0
+pydantic==1.9.0
+pydub==0.25.1
+pygments==2.8.0
+pynacl==1.5.0
+pyopenssl==19.1.0
+pyparsing==3.0.7
+pyrsistent==0.18.1
+pysocks==1.7.1
+python-dateutil==2.8.2
+python-etcd==0.4.5
+python-levenshtein==0.12.2
+python-multipart==0.0.5
+pytz==2021.1
+pyyaml==5.4.1
+pyzmq==22.3.0
+regex==2022.1.18
+requests==2.24.0
+resampy==0.2.2
+ruamel-yaml==0.15.87
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+send2trash==1.8.0
+sentry-sdk==1.5.4
+setuptools==50.3.1.post20201107
+shortuuid==1.0.8
+six==1.15.0
+smmap==5.0.0
+sniffio==1.2.0
+soundfile==0.10.3.post1
+soupsieve==2.2
+stack-data==0.1.4
+starlette==0.17.1
+subprocess32==3.5.4
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+threadpoolctl==3.0.0
+tokenizers==0.11.4
+tomli==1.2.3
+torch==1.10.2
+torchaudio==0.10.2
+torchelastic==0.2.2
+torchtext==0.9.1
+torchvision==0.9.1
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.17.0.dev0
+typing-extensions==4.0.1
+urllib3==1.25.11
+uvicorn==0.17.1
+wandb==0.12.9
+wcwidth==0.2.5
+webencodings==0.5.1
+wheel==0.35.1
+widgetsnbextension==3.5.2
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220201_142447-3hqii6h6/files/wandb-metadata.json

@@ -0,0 +1,65 @@
+{
+    "os": "Linux-4.15.0-151-generic-x86_64-with-glibc2.10",
+    "python": "3.8.8",
+    "heartbeatAt": "2022-02-01T14:24:49.335786",
+    "startedAt": "2022-02-01T14:24:47.897859",
+    "docker": null,
+    "gpu": "Tesla V100S-PCIE-32GB",
+    "gpu_count": 1,
+    "cpu_count": 60,
+    "cuda": null,
+    "args": [
+        "--dataset_name=mozilla-foundation/common_voice_8_0",
+        "--model_name_or_path=./checkpoint-18000",
+        "--dataset_config_name=fr",
+        "--tokenizer_name_or_path=./",
+        "--output_dir=./",
+        "--overwrite_output_dir",
+        "--num_train_epochs=1",
+        "--per_device_train_batch_size=64",
+        "--per_device_eval_batch_size=64",
+        "--gradient_accumulation_steps=1",
+        "--learning_rate=1e-4",
+        "--warmup_steps=2700",
+        "--length_column_name=input_length",
+        "--evaluation_strategy=steps",
+        "--text_column_name=sentence",
+        "--save_steps=500",
+        "--eval_steps=500",
+        "--logging_steps=100",
+        "--layerdrop=0.0",
+        "--activation_dropout=0.05",
+        "--save_total_limit=2",
+        "--freeze_feature_encoder",
+        "--feat_proj_dropout=0.0",
+        "--mask_time_prob=0.75",
+        "--mask_time_length=10",
+        "--mask_feature_prob=0.25",
+        "--mask_feature_length=10",
+        "--gradient_checkpointing",
+        "--report_to=wandb",
+        "--run_name=xls-r-300m-fr",
+        "--max_eval_samples=4500",
+        "--max_duration_in_seconds=10",
+        "--use_auth_token",
+        "--fp16",
+        "--group_by_length",
+        "--preprocessing_num_workers=64",
+        "--do_train=False",
+        "--do_eval",
+        "--load_best_model_at_end",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "run_speech_recognition_ctc.py",
+    "codePath": "run_speech_recognition_ctc.py",
+    "git": {
+        "remote": "https://huggingface.co/AlexN/xls-r-300m-fr",
+        "commit": "a37375f05121cad39aba4409ef22f6f71610efc6"
+    },
+    "email": "alexandrenap@hotmail.fr",
+    "root": "/workspace/xls-r-300m-fr",
+    "host": "job-1abccd0a-3293-4ffe-8274-9e8f841f653f",
+    "username": "ovh",
+    "executable": "/opt/conda/bin/python"
+}

wandb/run-20220201_142447-3hqii6h6/files/wandb-summary.json

@@ -0,0 +1 @@
+{"eval/loss": 0.22597630321979523, "eval/wer": 0.2948882012145466, "eval/runtime": 276.6037, "eval/samples_per_second": 16.157, "eval/steps_per_second": 0.253, "train/global_step": 0, "_runtime": 2, "_timestamp": 1643725490, "_step": 0}

wandb/run-20220201_142447-3hqii6h6/logs/debug-internal.log

@@ -0,0 +1,58 @@
+2022-02-01 14:24:48,994 INFO    MainThread:29947 [internal.py:wandb_internal():87] W&B internal server running at pid: 29947, started at: 2022-02-01 14:24:48.994283
+2022-02-01 14:24:48,998 INFO    WriterThread:29947 [datastore.py:open_for_write():77] open: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/run-3hqii6h6.wandb
+2022-02-01 14:24:48,999 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: check_version
+2022-02-01 14:24:49,002 DEBUG   SenderThread:29947 [sender.py:send():234] send: header
+2022-02-01 14:24:49,002 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: check_version
+2022-02-01 14:24:49,081 DEBUG   SenderThread:29947 [sender.py:send():234] send: run
+2022-02-01 14:24:49,273 INFO    SenderThread:29947 [dir_watcher.py:__init__():169] watching files in: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files
+2022-02-01 14:24:49,273 INFO    SenderThread:29947 [sender.py:_start_run_threads():804] run started: 3hqii6h6 with start time 1643725488
+2022-02-01 14:24:49,273 DEBUG   SenderThread:29947 [sender.py:send():234] send: summary
+2022-02-01 14:24:49,274 INFO    SenderThread:29947 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
+2022-02-01 14:24:49,276 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: run_start
+2022-02-01 14:24:49,335 DEBUG   HandlerThread:29947 [meta.py:__init__():40] meta init
+2022-02-01 14:24:49,335 DEBUG   HandlerThread:29947 [meta.py:__init__():54] meta init done
+2022-02-01 14:24:49,335 DEBUG   HandlerThread:29947 [meta.py:probe():214] probe
+2022-02-01 14:24:49,342 DEBUG   HandlerThread:29947 [meta.py:_setup_git():204] setup git
+2022-02-01 14:24:49,374 DEBUG   HandlerThread:29947 [meta.py:_setup_git():211] setup git done
+2022-02-01 14:24:49,374 DEBUG   HandlerThread:29947 [meta.py:_save_pip():58] save pip
+2022-02-01 14:24:49,375 DEBUG   HandlerThread:29947 [meta.py:_save_pip():72] save pip done
+2022-02-01 14:24:49,375 DEBUG   HandlerThread:29947 [meta.py:_save_conda():79] save conda
+2022-02-01 14:24:49,989 DEBUG   HandlerThread:29947 [meta.py:_save_conda():89] save conda done
+2022-02-01 14:24:49,989 DEBUG   HandlerThread:29947 [meta.py:probe():252] probe done
+2022-02-01 14:24:49,998 DEBUG   SenderThread:29947 [sender.py:send():234] send: files
+2022-02-01 14:24:49,999 INFO    SenderThread:29947 [sender.py:_save_file():939] saving file wandb-metadata.json with policy now
+2022-02-01 14:24:50,010 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: stop_status
+2022-02-01 14:24:50,011 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: stop_status
+2022-02-01 14:24:50,173 DEBUG   SenderThread:29947 [sender.py:send():234] send: config
+2022-02-01 14:24:50,176 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,176 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,177 WARNING SenderThread:29947 [sender.py:send_metric():897] Seen metric with glob (shouldnt happen)
+2022-02-01 14:24:50,177 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,177 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,177 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,177 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,177 DEBUG   SenderThread:29947 [sender.py:send():234] send: metric
+2022-02-01 14:24:50,178 DEBUG   SenderThread:29947 [sender.py:send():234] send: history
+2022-02-01 14:24:50,178 DEBUG   SenderThread:29947 [sender.py:send():234] send: summary
+2022-02-01 14:24:50,178 INFO    SenderThread:29947 [sender.py:_save_file():939] saving file wandb-summary.json with policy end
+2022-02-01 14:24:50,276 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_created():217] file/dir created: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/output.log
+2022-02-01 14:24:50,277 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_created():217] file/dir created: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/requirements.txt
+2022-02-01 14:24:50,277 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_created():217] file/dir created: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/conda-environment.yaml
+2022-02-01 14:24:50,278 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_created():217] file/dir created: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/wandb-metadata.json
+2022-02-01 14:24:50,278 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_created():217] file/dir created: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/wandb-summary.json
+2022-02-01 14:24:50,617 INFO    Thread-11 :29947 [upload_job.py:push():137] Uploaded file /tmp/tmpp56x1syiwandb/1qh281ys-wandb-metadata.json
+2022-02-01 14:24:52,275 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/output.log
+2022-02-01 14:24:54,276 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/output.log
+2022-02-01 14:25:05,175 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: stop_status
+2022-02-01 14:25:05,176 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: stop_status
+2022-02-01 14:25:17,592 DEBUG   SenderThread:29947 [sender.py:send():234] send: stats
+2022-02-01 14:25:20,294 INFO    Thread-8  :29947 [dir_watcher.py:_on_file_modified():230] file/dir modified: /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/files/config.yaml
+2022-02-01 14:25:20,335 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: stop_status
+2022-02-01 14:25:20,335 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: stop_status
+2022-02-01 14:25:35,486 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: stop_status
+2022-02-01 14:25:35,487 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: stop_status
+2022-02-01 14:25:47,927 DEBUG   SenderThread:29947 [sender.py:send():234] send: stats
+2022-02-01 14:25:50,662 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: stop_status
+2022-02-01 14:25:50,663 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: stop_status
+2022-02-01 14:26:05,830 DEBUG   HandlerThread:29947 [handler.py:handle_request():130] handle_request: stop_status
+2022-02-01 14:26:05,830 DEBUG   SenderThread:29947 [sender.py:send_request():248] send_request: stop_status

wandb/run-20220201_142447-3hqii6h6/logs/debug.log

@@ -0,0 +1,24 @@
+2022-02-01 14:24:47,902 INFO    MainThread:27520 [wandb_setup.py:_flush():71] setting env: {}
+2022-02-01 14:24:47,902 INFO    MainThread:27520 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-02-01 14:24:47,902 INFO    MainThread:27520 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/logs/debug.log
+2022-02-01 14:24:47,902 INFO    MainThread:27520 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-fr/wandb/run-20220201_142447-3hqii6h6/logs/debug-internal.log
+2022-02-01 14:24:47,903 INFO    MainThread:27520 [wandb_init.py:init():404] calling init triggers
+2022-02-01 14:24:47,903 INFO    MainThread:27520 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-02-01 14:24:47,903 INFO    MainThread:27520 [wandb_init.py:init():460] starting backend
+2022-02-01 14:24:47,903 INFO    MainThread:27520 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-02-01 14:24:48,004 INFO    MainThread:27520 [backend.py:ensure_launched():216] starting backend process...
+2022-02-01 14:24:48,099 INFO    MainThread:27520 [backend.py:ensure_launched():221] started backend process with pid: 29947
+2022-02-01 14:24:48,102 INFO    MainThread:27520 [wandb_init.py:init():469] backend started and connected
+2022-02-01 14:24:48,111 INFO    MainThread:27520 [wandb_init.py:init():533] updated telemetry
+2022-02-01 14:24:48,319 INFO    MainThread:27520 [wandb_init.py:init():563] communicating current version
+2022-02-01 14:24:49,079 INFO    MainThread:27520 [wandb_init.py:init():568] got version response 
+2022-02-01 14:24:49,079 INFO    MainThread:27520 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-02-01 14:24:49,275 INFO    MainThread:27520 [wandb_init.py:init():606] starting run threads in backend
+2022-02-01 14:24:50,008 INFO    MainThread:27520 [wandb_run.py:_console_start():1810] atexit reg
+2022-02-01 14:24:50,009 INFO    MainThread:27520 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-02-01 14:24:50,010 INFO    MainThread:27520 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-02-01 14:24:50,018 INFO    MainThread:27520 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-02-01 14:24:50,018 INFO    MainThread:27520 [wandb_init.py:init():633] run started, returning control to user process
+2022-02-01 14:24:50,021 INFO    MainThread:27520 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'architectures': ['Wav2Vec2ForCTC'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 218, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './checkpoint-18000', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.05, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 219, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.75, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.25, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': False, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 64, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 2700, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Feb01_14-18-51_job-1abccd0a-3293-4ffe-8274-9e8f841f653f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 2, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'xls-r-300m-fr', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'input_length', 'report_to': "['wandb']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'gradient_checkpointing': True, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'train_batch_size': 64, 'eval_batch_size': 64}
+2022-02-01 14:24:50,026 INFO    MainThread:27520 [wandb_watch.py:watch():43] Watching