Training in progress, step 500

.ipynb_checkpoints/run-checkpoint.sh

@@ -10,7 +10,7 @@ python run_speech_recognition_ctc.py \
 --per_device_train_batch_size="64" \
 --per_device_eval_batch_size="64" \
 --gradient_accumulation_steps="1" \
---learning_rate="1.5e-4" \
+--learning_rate="1e-4" \
 --warmup_steps="2700" \
 --length_column_name="input_length" \
 --evaluation_strategy="steps" \

added_tokens.json

@@ -0,0 +1 @@
+{"<s>": 216, "</s>": 217, "<pad>": 218}

config.json

@@ -6,7 +6,7 @@
   "add_adapter": false,
   "apply_spec_augment": true,
   "architectures": [
-    "Wav2Vec2ForPreTraining"
+    "Wav2Vec2ForCTC"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 1,

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7be356c0416d66c909300c8a24b255d6bc972bb2572b661bdcc3e0167f8aaba0
-size 1262817457
+oid sha256:3b2a3a9baeba423daf1f731e11f82192d46884b6ca3b5194a5c81fee49df28f5
+size 1262821553

run.sh

@@ -10,7 +10,7 @@ python run_speech_recognition_ctc.py \
 --per_device_train_batch_size="64" \
 --per_device_eval_batch_size="64" \
 --gradient_accumulation_steps="1" \
---learning_rate="1.5e-4" \
+--learning_rate="1e-4" \
 --warmup_steps="2700" \
 --length_column_name="input_length" \
 --evaluation_strategy="steps" \

special_tokens_map.json

@@ -0,0 +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}]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "do_lower_case": false, "word_delimiter_token": "|", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3515fcb3146dcedc28056bf8ff0c0b0a7c0ebdb32789529ea25826588fbd9491
+oid sha256:ea11d65b74bc35cdbdd475c519fd3f6ccaa32fbbc7747d0d176d1fc6825c659e
 size 3055

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220130_175417-3n44neww/logs/debug-internal.log
+run-20220130_191954-1mtmnz5y/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220130_175417-3n44neww/logs/debug.log
+run-20220130_191954-1mtmnz5y/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220130_175417-3n44neww
+run-20220130_191954-1mtmnz5y

wandb/run-20220130_191954-1mtmnz5y/files/output.log

@@ -0,0 +1,576 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  0%|▌                                                                                                                                                                    | 100/27860 [05:42<13:48:16,  1.79s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|█▏                                                                                                                                                                   | 199/27860 [11:22<15:07:43,  1.97s/it]
+{'loss': 11.9694, 'learning_rate': 7.333333333333334e-06, 'epoch': 0.03}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|█▊                                                                                                                                                                   | 300/27860 [17:06<13:37:50,  1.78s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|██▎                                                                                                                                                                  | 398/27860 [22:45<15:17:03,  2.00s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|██▉                                                                                                                                                                  | 500/27860 [28:32<14:14:02,  1.87s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 4469
+  Batch size = 64
+{'loss': 6.0197, 'learning_rate': 1.840740740740741e-05, 'epoch': 0.07}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 70/70 [03:40<00:00,  3.11s/it]
+
+Configuration saved in ./checkpoint-500/config.json
+Model weights saved in ./checkpoint-500/pytorch_model.bin
+Configuration saved in ./checkpoint-500/preprocessor_config.json

wandb/run-20220130_191954-1mtmnz5y/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-20220130_191954-1mtmnz5y/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": "2022-01-30T19:19:56.155478",
+    "startedAt": "2022-01-30T19:19:54.895374",
+    "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=facebook/wav2vec2-xls-r-300m",
+        "--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": "ef5fb31f65fbbcae817277ba32c1f3a0c4bef31a"
+    },
+    "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-20220130_191954-1mtmnz5y/logs/debug.log

@@ -0,0 +1,24 @@
+2022-01-30 19:19:54,899 INFO    MainThread:26084 [wandb_setup.py:_flush():71] setting env: {}
+2022-01-30 19:19:54,899 INFO    MainThread:26084 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-01-30 19:19:54,900 INFO    MainThread:26084 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-fr/wandb/run-20220130_191954-1mtmnz5y/logs/debug.log
+2022-01-30 19:19:54,900 INFO    MainThread:26084 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-fr/wandb/run-20220130_191954-1mtmnz5y/logs/debug-internal.log
+2022-01-30 19:19:54,900 INFO    MainThread:26084 [wandb_init.py:init():404] calling init triggers
+2022-01-30 19:19:54,900 INFO    MainThread:26084 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-01-30 19:19:54,900 INFO    MainThread:26084 [wandb_init.py:init():460] starting backend
+2022-01-30 19:19:54,901 INFO    MainThread:26084 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-01-30 19:19:54,987 INFO    MainThread:26084 [backend.py:ensure_launched():216] starting backend process...
+2022-01-30 19:19:55,070 INFO    MainThread:26084 [backend.py:ensure_launched():221] started backend process with pid: 55777
+2022-01-30 19:19:55,073 INFO    MainThread:26084 [wandb_init.py:init():469] backend started and connected
+2022-01-30 19:19:55,082 INFO    MainThread:26084 [wandb_init.py:init():533] updated telemetry
+2022-01-30 19:19:55,252 INFO    MainThread:26084 [wandb_init.py:init():563] communicating current version
+2022-01-30 19:19:55,947 INFO    MainThread:26084 [wandb_init.py:init():568] got version response 
+2022-01-30 19:19:55,948 INFO    MainThread:26084 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-01-30 19:19:56,146 INFO    MainThread:26084 [wandb_init.py:init():606] starting run threads in backend
+2022-01-30 19:19:56,763 INFO    MainThread:26084 [wandb_run.py:_console_start():1810] atexit reg
+2022-01-30 19:19:56,764 INFO    MainThread:26084 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-01-30 19:19:56,764 INFO    MainThread:26084 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-01-30 19:19:56,771 INFO    MainThread:26084 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-01-30 19:19:56,771 INFO    MainThread:26084 [wandb_init.py:init():633] run started, returning control to user process
+2022-01-30 19:19:56,774 INFO    MainThread:26084 [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': 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/Jan30_18-03-27_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}
+2022-01-30 19:19:56,778 INFO    MainThread:26084 [wandb_watch.py:watch():43] Watching