Training in progress, step 500

.ipynb_checkpoints/run_speech_recognition_ctc-checkpoint.py

@@ -522,10 +522,11 @@ def main():
     # one local process can concurrently download model & vocab.
 
     # load feature_extractor and tokenizer
-    tokenizer = Wav2Vec2CTCTokenizer(tokenizer_name_or_path, 
-                                     use_auth_token=data_args.use_auth_token,
-                                     **tokenizer_kwargs,
-                                    )
+    tokenizer = Wav2Vec2CTCTokenizer.from_pretrained(
+        tokenizer_name_or_path, 
+        use_auth_token=data_args.use_auth_token,
+        **tokenizer_kwargs,
+    )
     feature_extractor = AutoFeatureExtractor.from_pretrained(
         model_args.model_name_or_path, cache_dir=model_args.cache_dir, use_auth_token=data_args.use_auth_token
     )

.ipynb_checkpoints/vocab-checkpoint.json

@@ -0,0 +1 @@
+{"'": 1, "(": 2, ")": 3, "*": 4, ".": 5, "/": 6, "1": 7, "2": 8, "=": 9, "C": 10, "E": 11, "N": 12, "Q": 13, "R": 14, "Z": 15, "`": 16, "a": 17, "b": 18, "c": 19, "d": 20, "e": 21, "f": 22, "g": 23, "h": 24, "i": 25, "j": 26, "k": 27, "l": 28, "m": 29, "n": 30, "o": 31, "p": 32, "q": 33, "r": 34, "s": 35, "t": 36, "u": 37, "v": 38, "w": 39, "x": 40, "y": 41, "z": 42, "{": 43, "|": 0, "}": 45, "~": 46, "\u00a7": 47, "\u00ab": 48, "\u00ae": 49, "\u00b0": 50, "\u00b1": 51, "\u00b7": 52, "\u00bb": 53, "\u00d7": 54, "\u00df": 55, "\u00e6": 56, "\u00e7": 57, "\u00f0": 58, "\u00f8": 59, "\u00fe": 60, "\u0111": 61, "\u0127": 62, "\u0131": 63, "\u0142": 64, "\u0153": 65, "\u01c0": 66, "\u01c3": 67, "\u0251": 68, "\u0259": 69, "\u0268": 70, "\u0289": 71, "\u0294": 72, "\u02bb": 73, "\u02bc": 74, "\u02bd": 75, "\u02be": 76, "\u02bf": 77, "\u02d0": 78, "\u03b1": 79, "\u03b2": 80, "\u03b3": 81, "\u03b4": 82, "\u03b5": 83, "\u03b6": 84, "\u03b7": 85, "\u03b8": 86, "\u03b9": 87, "\u03ba": 88, "\u03bb": 89, "\u03bc": 90, "\u03bd": 91, "\u03bf": 92, "\u03c0": 93, "\u03c1": 94, "\u03c2": 95, "\u03c3": 96, "\u03c4": 97, "\u03c5": 98, "\u03c6": 99, "\u03c7": 100, "\u03c8": 101, "\u03c9": 102, "\u0430": 103, "\u0433": 104, "\u0435": 105, "\u0437": 106, "\u0438": 107, "\u043a": 108, "\u043c": 109, "\u043d": 110, "\u043e": 111, "\u043f": 112, "\u0440": 113, "\u0446": 114, "\u0447": 115, "\u044d": 116, "\u044f": 117, "\u0454": 118, "\u0456": 119, "\u0458": 120, "\u045f": 121, "\u04ab": 122, "\u04cc": 123, "\u0563": 124, "\u0566": 125, "\u0627": 126, "\u0628": 127, "\u0629": 128, "\u062f": 129, "\u0631": 130, "\u0644": 131, "\u0645": 132, "\u0646": 133, "\u0648": 134, "\u064a": 135, "\u1100": 136, "\u1106": 137, "\u1109": 138, "\u110c": 139, "\u1161": 140, "\u1162": 141, "\u1165": 142, "\u1169": 143, "\u1175": 144, "\u11a8": 145, "\u11b7": 146, "\u11b8": 147, "\u11bc": 148, "\u1240": 149, "\u12a8": 150, "\u12c8": 151, "\u12f0": 152, "\u1300": 153, "\u2010": 154, "\u2013": 155, "\u2014": 156, "\u2015": 157, "\u2019": 158, "\u201e": 159, "\u2020": 160, "\u2032": 161, "\u2039": 162, "\u203a": 163, "\u2044": 164, "\u20bd": 165, "\u2192": 166, "\u2194": 167, "\u2205": 168, "\u2206": 169, "\u2208": 170, "\u2212": 171, "\u221e": 172, "\u2228": 173, "\u223c": 174, "\u2265": 175, "\u22a8": 176, "\u22c5": 177, "\u2500": 178, "\u2609": 179, "\u2c45": 180, "\u2c4e": 181, "\u3044": 182, "\u3046": 183, "\u305f": 184, "\u3064": 185, "\u306e": 186, "\u3072": 187, "\u3078": 188, "\u307e": 189, "\u3080": 190, "\u3081": 191, "\u3082": 192, "\u3084": 193, "\u4e09": 194, "\u4e39": 195, "\u4e43": 196, "\u4eac": 197, "\u4fdd": 198, "\u5317": 199, "\u53b3": 200, "\u5b87": 201, "\u626c": 202, "\u6587": 203, "\u661f": 204, "\u672f": 205, "\u675c": 206, "\u6d25": 207, "\u7261": 208, "\u750c": 209, "\u7f8e": 210, "\u897f": 211, "\u8cb4": 212, "\u9752": 213, "\u9986": 214, "\ua751": 215, "[UNK]": 215, "[PAD]": 216}

added_tokens.json

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

config.json

@@ -0,0 +1,107 @@
+{
+  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+  "activation_dropout": 0.1,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForCTC"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 768,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": true,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "mean",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": true,
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_dropout": 0.0,
+  "feat_extract_norm": "layer",
+  "feat_proj_dropout": 0.0,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.33,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.75,
+  "model_type": "wav2vec2",
+  "num_adapter_layers": 3,
+  "num_attention_heads": 16,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 24,
+  "num_negatives": 100,
+  "output_hidden_size": 1024,
+  "pad_token_id": 216,
+  "proj_codevector_dim": 768,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0.dev0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 218,
+  "xvector_output_dim": 512
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:472a00d6c3344b86c7803638519386c0a1eb56d7f282665bd5d7c54ec88a7de2
+size 1262817457

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}]}

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": "|", "config": null, "tokenizer_type": "wav2vec2", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045ff4a8456a52acfb08e668118d28bcb89545214b55b6b4b0122ab5c2b1ef4e
+size 3055

vocab.json

@@ -0,0 +1 @@
+{"'": 1, "(": 2, ")": 3, "*": 4, ".": 5, "/": 6, "1": 7, "2": 8, "=": 9, "C": 10, "E": 11, "N": 12, "Q": 13, "R": 14, "Z": 15, "`": 16, "a": 17, "b": 18, "c": 19, "d": 20, "e": 21, "f": 22, "g": 23, "h": 24, "i": 25, "j": 26, "k": 27, "l": 28, "m": 29, "n": 30, "o": 31, "p": 32, "q": 33, "r": 34, "s": 35, "t": 36, "u": 37, "v": 38, "w": 39, "x": 40, "y": 41, "z": 42, "{": 43, "|": 0, "}": 45, "~": 46, "§": 47, "«": 48, "®": 49, "°": 50, "±": 51, "·": 52, "»": 53, "×": 54, "ß": 55, "æ": 56, "ç": 57, "ð": 58, "ø": 59, "þ": 60, "đ": 61, "ħ": 62, "ı": 63, "ł": 64, "œ": 65, "ǀ": 66, "ǃ": 67, "ɑ": 68, "ə": 69, "ɨ": 70, "ʉ": 71, "ʔ": 72, "ʻ": 73, "ʼ": 74, "ʽ": 75, "ʾ": 76, "ʿ": 77, "ː": 78, "α": 79, "β": 80, "γ": 81, "δ": 82, "ε": 83, "ζ": 84, "η": 85, "θ": 86, "ι": 87, "κ": 88, "λ": 89, "μ": 90, "ν": 91, "ο": 92, "π": 93, "ρ": 94, "ς": 95, "σ": 96, "τ": 97, "υ": 98, "φ": 99, "χ": 100, "ψ": 101, "ω": 102, "а": 103, "г": 104, "е": 105, "з": 106, "и": 107, "к": 108, "м": 109, "н": 110, "о": 111, "п": 112, "р": 113, "ц": 114, "ч": 115, "э": 116, "я": 117, "є": 118, "і": 119, "ј": 120, "џ": 121, "ҫ": 122, "ӌ": 123, "գ": 124, "զ": 125, "ا": 126, "ب": 127, "ة": 128, "د": 129, "ر": 130, "ل": 131, "م": 132, "ن": 133, "و": 134, "ي": 135, "ᄀ": 136, "ᄆ": 137, "ᄉ": 138, "ᄌ": 139, "ᅡ": 140, "ᅢ": 141, "ᅥ": 142, "ᅩ": 143, "ᅵ": 144, "ᆨ": 145, "ᆷ": 146, "ᆸ": 147, "ᆼ": 148, "ቀ": 149, "ከ": 150, "ወ": 151, "ደ": 152, "ጀ": 153, "‐": 154, "–": 155, "—": 156, "―": 157, "’": 158, "„": 159, "†": 160, "′": 161, "‹": 162, "›": 163, "⁄": 164, "₽": 165, "→": 166, "↔": 167, "∅": 168, "∆": 169, "∈": 170, "−": 171, "∞": 172, "∨": 173, "∼": 174, "≥": 175, "⊨": 176, "⋅": 177, "─": 178, "☉": 179, "ⱅ": 180, "ⱎ": 181, "い": 182, "う": 183, "た": 184, "つ": 185, "の": 186, "ひ": 187, "へ": 188, "ま": 189, "む": 190, "め": 191, "も": 192, "や": 193, "三": 194, "丹": 195, "乃": 196, "京": 197, "保": 198, "北": 199, "厳": 200, "宇": 201, "扬": 202, "文": 203, "星": 204, "术": 205, "杜": 206, "津": 207, "牡": 208, "甌": 209, "美": 210, "西": 211, "貴": 212, "青": 213, "馆": 214, "ꝑ": 215, "[UNK]": 215, "[PAD]": 216}

wandb/debug-internal.log

@@ -0,0 +1 @@
+run-20220129_131141-h6nhqm30/logs/debug-internal.log

wandb/debug.log

@@ -0,0 +1 @@
+run-20220129_131141-h6nhqm30/logs/debug.log

wandb/latest-run

@@ -0,0 +1 @@
+run-20220129_131141-h6nhqm30

wandb/run-20220129_131141-h6nhqm30/files/output.log

@@ -0,0 +1,529 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  0%|▋                                                                                                                                                              | 100/21520 [04:25<9:53:42,  1.66s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|█▍                                                                                                                                                            | 199/21520 [08:51<10:08:31,  1.71s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  1%|██▏                                                                                                                                                            | 300/21520 [13:20<9:42:10,  1.65s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|██▉                                                                                                                                                            | 399/21520 [17:44<9:49:47,  1.68s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|███▋                                                                                                                                                           | 500/21520 [22:14<9:36:18,  1.65s/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 = 1839
+  Batch size = 64
+{'loss': 5.4101, 'learning_rate': 2.3239999999999998e-05, 'epoch': 0.12}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Configuration saved in ./checkpoint-500/config.json
+{'eval_loss': 5.053680896759033, 'eval_wer': 1.0, 'eval_runtime': 62.0508, 'eval_samples_per_second': 29.637, 'eval_steps_per_second': 0.467, 'epoch': 0.12}
+Model weights saved in ./checkpoint-500/pytorch_model.bin
+Configuration saved in ./checkpoint-500/preprocessor_config.json

wandb/run-20220129_131141-h6nhqm30/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-20220129_131141-h6nhqm30/files/wandb-metadata.json

@@ -0,0 +1,64 @@
+{
+    "os": "Linux-4.15.0-151-generic-x86_64-with-glibc2.10",
+    "python": "3.8.8",
+    "heartbeatAt": "2022-01-29T13:11:43.886807",
+    "startedAt": "2022-01-29T13:11:41.626227",
+    "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",
+        "--output_dir=./",
+        "--overwrite_output_dir",
+        "--num_train_epochs=5",
+        "--per_device_train_batch_size=64",
+        "--per_device_eval_batch_size=64",
+        "--gradient_accumulation_steps=1",
+        "--learning_rate=7e-5",
+        "--warmup_steps=1500",
+        "--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=0.1",
+        "--save_total_limit=3",
+        "--freeze_feature_encoder",
+        "--feat_proj_dropout=0.0",
+        "--mask_time_prob=0.75",
+        "--mask_time_length=10",
+        "--mask_feature_prob=0.33",
+        "--mask_feature_length=10",
+        "--gradient_checkpointing",
+        "--report_to=wandb",
+        "--run_name=xls-r-300m-fr",
+        "--max_eval_samples=4000",
+        "--max_duration_in_seconds=5",
+        "--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": "44c47390840b2e07543aa79514aa51086a0ff3cf"
+    },
+    "email": "[email protected]",
+    "root": "/workspace/xls-r-300m-fr",
+    "host": "job-1abccd0a-3293-4ffe-8274-9e8f841f653f",
+    "username": "ovh",
+    "executable": "/opt/conda/bin/python"
+}

wandb/run-20220129_131141-h6nhqm30/logs/debug.log

@@ -0,0 +1,24 @@
+2022-01-29 13:11:41,630 INFO    MainThread:44227 [wandb_setup.py:_flush():71] setting env: {}
+2022-01-29 13:11:41,630 INFO    MainThread:44227 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-01-29 13:11:41,631 INFO    MainThread:44227 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-fr/wandb/run-20220129_131141-h6nhqm30/logs/debug.log
+2022-01-29 13:11:41,631 INFO    MainThread:44227 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-fr/wandb/run-20220129_131141-h6nhqm30/logs/debug-internal.log
+2022-01-29 13:11:41,631 INFO    MainThread:44227 [wandb_init.py:init():404] calling init triggers
+2022-01-29 13:11:41,631 INFO    MainThread:44227 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-01-29 13:11:41,631 INFO    MainThread:44227 [wandb_init.py:init():460] starting backend
+2022-01-29 13:11:41,631 INFO    MainThread:44227 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-01-29 13:11:42,043 INFO    MainThread:44227 [backend.py:ensure_launched():216] starting backend process...
+2022-01-29 13:11:42,437 INFO    MainThread:44227 [backend.py:ensure_launched():221] started backend process with pid: 13445
+2022-01-29 13:11:42,439 INFO    MainThread:44227 [wandb_init.py:init():469] backend started and connected
+2022-01-29 13:11:42,449 INFO    MainThread:44227 [wandb_init.py:init():533] updated telemetry
+2022-01-29 13:11:43,278 INFO    MainThread:44227 [wandb_init.py:init():563] communicating current version
+2022-01-29 13:11:43,680 INFO    MainThread:44227 [wandb_init.py:init():568] got version response 
+2022-01-29 13:11:43,681 INFO    MainThread:44227 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-01-29 13:11:43,876 INFO    MainThread:44227 [wandb_init.py:init():606] starting run threads in backend
+2022-01-29 13:11:44,463 INFO    MainThread:44227 [wandb_run.py:_console_start():1810] atexit reg
+2022-01-29 13:11:44,464 INFO    MainThread:44227 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-01-29 13:11:44,464 INFO    MainThread:44227 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-01-29 13:11:44,471 INFO    MainThread:44227 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-01-29 13:11:44,471 INFO    MainThread:44227 [wandb_init.py:init():633] run started, returning control to user process
+2022-01-29 13:11:44,474 INFO    MainThread:44227 [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': 216, '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': 0.1, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 218, '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': 0.33, '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': 7e-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': 5.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 1500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jan29_11-53-08_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': 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': '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}
+2022-01-29 13:11:44,479 INFO    MainThread:44227 [wandb_watch.py:watch():43] Watching