Training in progress, step 500

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "marinone94/xls-r-300m-sv-robust",
+  "_name_or_path": "KBLab/wav2vec2-large-voxrex",
   "activation_dropout": 0.1,
   "adapter_kernel_size": 3,
   "adapter_stride": 2,
@@ -59,12 +59,20 @@
   "intermediate_size": 4096,
   "layer_norm_eps": 1e-05,
   "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
   "mask_feature_length": 64,
   "mask_feature_min_masks": 0,
   "mask_feature_prob": 0.25,
   "mask_time_length": 10,
   "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
   "mask_time_prob": 0.75,
+  "mask_time_selection": "static",
   "model_type": "wav2vec2",
   "num_adapter_layers": 3,
   "num_attention_heads": 16,

preprocessor_config.json

@@ -4,7 +4,6 @@
   "feature_size": 1,
   "padding_side": "right",
   "padding_value": 0,
-  "processor_class": "Wav2Vec2ProcessorWithLM",
   "return_attention_mask": true,
   "sampling_rate": 16000
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849f22348838353270f3fea71da7123aea0c4d81f944d73fe8359395ee3e8678
+oid sha256:34669b63c1997f98af6a828a1f63b66b0658b43051e123f27c37b2b1df710b81
 size 1262075377

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": "<s>", "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": "</s>", "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}]}
+{"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": "<s>", "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": "</s>", "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": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

tokenizer_config.json

@@ -1 +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": "marinone94/xls-r-300m-sv-robust", "tokenizer_class": "Wav2Vec2CTCTokenizer"}
+{"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 sha256:0efc7aad7fd151e94de194f50e712cd8d3c82a2cf2ccee51d253c9130af43c3a
-size 2991
+oid sha256:e93512254853170601d69416635484a8a91b518c58d4ec3e92cb2e1d96df8639
+size 3055

wandb/debug-internal.log

@@ -0,0 +1 @@
+run-20220127_103723-scy0vyln/logs/debug-internal.log

wandb/debug.log

@@ -0,0 +1 @@
+run-20220127_103723-scy0vyln/logs/debug.log

wandb/latest-run

@@ -0,0 +1 @@
+run-20220127_103723-scy0vyln

wandb/run-20220127_103723-scy0vyln/files/output.log

@@ -0,0 +1,391 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|▉                                                                                                                                                           | 99/17200 [02:04<4:11:41,  1.13it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|█▊                                                                                                                                                         | 199/17200 [04:10<4:20:58,  1.09it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|██▋                                                                                                                                                        | 299/17200 [06:17<4:09:48,  1.13it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|███▌                                                                                                                                                       | 400/17200 [08:28<8:06:09,  1.74s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  3%|████▌                                                                                                                                                      | 500/17200 [10:34<7:57:23,  1.72s/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 = 4620
+  Batch size = 8
+  1%|█▉                                                                                                                                                               | 7/578 [00:01<02:20,  4.07it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 578/578 [02:10<00:00,  4.78it/s]
+
+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-20220127_103723-scy0vyln/files/requirements.txt

@@ -0,0 +1,164 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+analytics-python==1.4.0
+appdirs==1.4.4
+argon2-cffi==20.1.0
+async-generator==1.10
+async-timeout==4.0.2
+attrs==21.1.0
+audioread==2.1.9
+backcall==0.2.0
+backoff==1.10.0
+bcrypt==3.2.0
+beautifulsoup4==4.9.3
+bleach==3.3.0
+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==1.17.1.dev0
+decorator==4.4.2
+defusedxml==0.7.1
+dill==0.3.4
+dnspython==2.1.0
+docker-pycreds==0.4.0
+entrypoints==0.3
+ffmpy==0.3.0
+filelock==3.0.12
+flask-cachebuster==1.0.0
+flask-cors==3.0.10
+flask-login==0.5.0
+flask==2.0.2
+fonttools==4.28.5
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.26
+glob2==0.7
+gradio==2.7.0
+huggingface-hub==0.4.0
+idna==2.10
+ipykernel==5.5.4
+ipython-genutils==0.2.0
+ipython==7.21.0
+ipywidgets==7.6.3
+itsdangerous==2.0.1
+jedi==0.17.0
+jinja2==3.0.3
+jiwer==2.3.0
+joblib==1.1.0
+json5==0.9.5
+jsonschema==3.2.0
+jupyter-client==6.1.12
+jupyter-core==4.7.1
+jupyterlab-pygments==0.1.2
+jupyterlab-server==1.2.0
+jupyterlab-widgets==1.0.0
+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==2.0.1
+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==5.2.0
+multiprocess==0.70.12.2
+nano==0.10.0
+nbclient==0.5.3
+nbconvert==6.0.7
+nbformat==5.1.3
+nest-asyncio==1.5.1
+notebook==6.3.0
+numba==0.55.0
+numpy==1.19.2
+olefile==0.46
+packaging==20.9
+pandas==1.3.5
+pandocfilters==1.4.3
+paramiko==2.9.2
+parso==0.8.1
+pathtools==0.1.2
+pexpect==4.8.0
+pickleshare==0.7.5
+pillow==8.1.2
+pip==21.3.1
+pkginfo==1.7.0
+pooch==1.5.2
+prometheus-client==0.10.1
+promise==2.3
+prompt-toolkit==3.0.8
+protobuf==3.19.3
+psutil==5.8.0
+ptyprocess==0.7.0
+pyarrow==6.0.1
+pycosat==0.6.3
+pycparser==2.20
+pycryptodome==3.12.0
+pydub==0.25.1
+pygments==2.8.0
+pynacl==1.5.0
+pyopenssl==19.1.0
+pyparsing==2.4.7
+pyrsistent==0.17.3
+pysocks==1.7.1
+python-dateutil==2.8.1
+python-etcd==0.4.5
+python-levenshtein==0.12.2
+pytz==2021.1
+pyyaml==5.4.1
+pyzmq==22.0.3
+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==1.5.0
+sentry-sdk==1.5.3
+setuptools==50.3.1.post20201107
+shortuuid==1.0.8
+six==1.15.0
+smmap==5.0.0
+soundfile==0.10.3.post1
+soupsieve==2.2
+subprocess32==3.5.4
+termcolor==1.1.0
+terminado==0.9.4
+testpath==0.4.4
+threadpoolctl==3.0.0
+tokenizers==0.11.4
+torch==1.10.1
+torchaudio==0.10.1
+torchelastic==0.2.2
+torchtext==0.9.1
+torchvision==0.9.1
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.0.5
+transformers==4.16.0.dev0
+typing-extensions==3.7.4.3
+urllib3==1.25.11
+wandb==0.12.9
+wcwidth==0.2.5
+webencodings==0.5.1
+werkzeug==2.0.2
+wheel==0.35.1
+widgetsnbextension==3.5.1
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0

wandb/run-20220127_103723-scy0vyln/files/wandb-metadata.json

@@ -0,0 +1,76 @@
+{
+    "os": "Linux-5.11.0-37-generic-x86_64-with-glibc2.10",
+    "python": "3.8.8",
+    "heartbeatAt": "2022-01-27T10:37:24.935995",
+    "startedAt": "2022-01-27T10:37:23.634817",
+    "docker": null,
+    "gpu": "Tesla V100S-PCIE-32GB",
+    "gpu_count": 1,
+    "cpu_count": 60,
+    "cuda": null,
+    "args": [
+        "--dataset_name=mozilla-foundation/common_voice_7_0",
+        "--model_name_or_path=KBLab/wav2vec2-large-voxrex",
+        "--dataset_config_name=sv-SE",
+        "--output_dir=./",
+        "--overwrite_output_dir",
+        "--num_train_epochs=50",
+        "--per_device_train_batch_size=8",
+        "--per_device_eval_batch_size=8",
+        "--gradient_accumulation_steps=4",
+        "--learning_rate=7.5e-5",
+        "--warmup_steps=2000",
+        "--length_column_name=input_length",
+        "--evaluation_strategy=steps",
+        "--text_column_name=sentence",
+        "--chars_to_ignore",
+        ",",
+        "?",
+        ".",
+        "!",
+        "-",
+        ";",
+        ":",
+        "\"",
+        "\u201c",
+        "%",
+        "\u2018",
+        "\u201d",
+        "\ufffd",
+        "\u2014",
+        "\u2019",
+        "\u2026",
+        "\u2013",
+        "--save_steps=500",
+        "--eval_steps=500",
+        "--logging_steps=100",
+        "--layerdrop=0.0",
+        "--activation_dropout=0.1",
+        "--save_total_limit=3",
+        "--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=64",
+        "--gradient_checkpointing",
+        "--use_auth_token",
+        "--fp16",
+        "--group_by_length",
+        "--do_train",
+        "--do_eval",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "run_speech_recognition_ctc.py",
+    "codePath": "run_speech_recognition_ctc.py",
+    "git": {
+        "remote": "https://huggingface.co/marinone94/xls-r-300m-sv-robust",
+        "commit": "b572cfd9a72986bbd88e7fb7e16805985d5ef760"
+    },
+    "email": "marinone94@gmail.com",
+    "root": "/workspace/xls-r-300m-sv-robust",
+    "host": "job-38746614-58de-4025-b727-ddb5a9d90aee",
+    "username": "ovh",
+    "executable": "/opt/conda/bin/python"
+}

wandb/run-20220127_103723-scy0vyln/logs/debug.log

@@ -0,0 +1,25 @@
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_setup.py:_flush():71] setting env: {'project': 'xls-r-300m-sv-robust'}
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-sv-robust/wandb/run-20220127_103723-scy0vyln/logs/debug.log
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-sv-robust/wandb/run-20220127_103723-scy0vyln/logs/debug-internal.log
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_init.py:init():404] calling init triggers
+2022-01-27 10:37:23,636 INFO    MainThread:1976170 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-01-27 10:37:23,637 INFO    MainThread:1976170 [wandb_init.py:init():460] starting backend
+2022-01-27 10:37:23,637 INFO    MainThread:1976170 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-01-27 10:37:23,722 INFO    MainThread:1976170 [backend.py:ensure_launched():216] starting backend process...
+2022-01-27 10:37:23,804 INFO    MainThread:1976170 [backend.py:ensure_launched():221] started backend process with pid: 1977561
+2022-01-27 10:37:23,807 INFO    MainThread:1976170 [wandb_init.py:init():469] backend started and connected
+2022-01-27 10:37:23,817 INFO    MainThread:1976170 [wandb_init.py:init():533] updated telemetry
+2022-01-27 10:37:23,979 INFO    MainThread:1976170 [wandb_init.py:init():563] communicating current version
+2022-01-27 10:37:24,696 INFO    MainThread:1976170 [wandb_init.py:init():568] got version response 
+2022-01-27 10:37:24,696 INFO    MainThread:1976170 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-01-27 10:37:24,927 INFO    MainThread:1976170 [wandb_init.py:init():606] starting run threads in backend
+2022-01-27 10:37:25,565 INFO    MainThread:1976170 [wandb_run.py:_console_start():1810] atexit reg
+2022-01-27 10:37:25,566 INFO    MainThread:1976170 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-01-27 10:37:25,567 INFO    MainThread:1976170 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-01-27 10:37:25,572 INFO    MainThread:1976170 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-01-27 10:37:25,572 INFO    MainThread:1976170 [wandb_init.py:init():633] run started, returning control to user process
+2022-01-27 10:37:25,575 INFO    MainThread:1976170 [wandb_run.py:_config_callback():956] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, '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': 34, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'KBLab/wav2vec2-large-voxrex', 'transformers_version': '4.16.0.dev0', 'feat_extract_dropout': 0.0, 'mask_channel_length': 10, 'mask_channel_min_space': 1, 'mask_channel_other': 0.0, 'mask_channel_prob': 0.0, 'mask_channel_selection': 'static', 'mask_time_min_space': 1, 'mask_time_other': 0.0, 'mask_time_selection': 'static', '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': 0.1, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 37, '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': 64, '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': 8, 'per_device_eval_batch_size': 8, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 4, 'eval_accumulation_steps': 'None', 'learning_rate': 7.5e-05, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 50.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 2000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jan27_10-34-00_job-38746614-58de-4025-b727-ddb5a9d90aee', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 3, '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': '2022-01-27T10:34:01.114533', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': False, 'metric_for_best_model': 'None', 'greater_is_better': 'None', 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, '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': 8, 'eval_batch_size': 8}
+2022-01-27 10:37:25,580 INFO    MainThread:1976170 [wandb_watch.py:watch():43] Watching