Training in progress, step 2500

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20220306_154547-4pqitlp3/run-4pqitlp3.wandb filter=lfs diff=lfs merge=lfs -text

.idea/misc.xml

@@ -8,14 +8,14 @@
           <option name="caretOffset" value="0" />
           <option name="fileUrl" value="file://$PROJECT_DIR$/create_model.py" />
         </OpenedFileInfo>
-        <OpenedFileInfo>
-          <option name="caretOffset" value="4372" />
-          <option name="fileUrl" value="file://$PROJECT_DIR$/run_speech_recognition_seq2seq.py" />
-        </OpenedFileInfo>
         <OpenedFileInfo>
           <option name="caretOffset" value="0" />
           <option name="fileUrl" value="file://$PROJECT_DIR$/run_librispeech.sh" />
         </OpenedFileInfo>
+        <OpenedFileInfo>
+          <option name="caretOffset" value="4372" />
+          <option name="fileUrl" value="file://$PROJECT_DIR$/run_speech_recognition_seq2seq.py" />
+        </OpenedFileInfo>
       </list>
     </option>
   </component>

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f301fe04b56a00bc89f821491fdbc666865ef4aaf78ef64678844e45ac6799
+oid sha256:99a684e305cc3497307beadcf4d6ff43f628217105530d1e47db3a4d80df0bda
 size 3210531882

run_librispeech.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-CUDA_VISIBLE_DEVICES=1 python run_speech_recognition_seq2seq.py \
+CUDA_VISIBLE_DEVICES=0 python run_speech_recognition_seq2seq.py \
 	--dataset_name="librispeech_asr" \
 	--model_name_or_path="./" \
 	--tokenizer_name="./" \
@@ -10,18 +10,18 @@ CUDA_VISIBLE_DEVICES=1 python run_speech_recognition_seq2seq.py \
 	--preprocessing_num_workers="1" \
 	--length_column_name="input_length" \
 	--overwrite_output_dir \
-	--num_train_epochs="3" \
-	--per_device_train_batch_size="14" \
-	--per_device_eval_batch_size="14" \
-	--gradient_accumulation_steps="8" \
+	--num_train_epochs="20" \
+	--per_device_train_batch_size="8" \
+	--per_device_eval_batch_size="8" \
+	--gradient_accumulation_steps="4" \
 	--generation_max_length="40" \
 	--generation_num_beams="1" \
-	--learning_rate="1e-3" \
-	--warmup_steps="500" \
+	--learning_rate="1e-4" \
+	--warmup_steps="1000" \
 	--evaluation_strategy="steps" \
 	--text_column_name="text" \
-	--save_steps="500" \
-	--eval_steps="500" \
+	--save_steps="2500" \
+	--eval_steps="2500" \
 	--logging_steps="1" \
 	--save_total_limit="1" \
 	--freeze_feature_encoder \

runs/Feb26_17-07-09_sanchit--v100/1645895266.693364/events.out.tfevents.1645895266.sanchit--v100.205230.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73ca80c6382726379e0c57341eee4d57704a013fcb2f6fc1ed8e4027fe8b6330
+size 4964

runs/Feb26_17-07-09_sanchit--v100/events.out.tfevents.1645895266.sanchit--v100.205230.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98839aaece18f6320e0d76e929501b38fcef4c5fe1e544a30fd9c6cd7e4c1f9b
+size 87288

runs/Feb26_17-45-46_sanchit--v100/1645897583.1805394/events.out.tfevents.1645897583.sanchit--v100.205370.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe06bff70f33eeea9d90ede615c9df1263c803caf8341471eb27e7df0ee2759
+size 4964

runs/Feb26_17-45-46_sanchit--v100/events.out.tfevents.1645897583.sanchit--v100.205370.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb3b72a5481482e1bedd7ebcc231588e9d21931efaf7f2c5c7f5165420e785b2
+size 79438

runs/Feb26_18-51-14_sanchit--v100/1645901511.7199447/events.out.tfevents.1645901511.sanchit--v100.205521.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72c20123a38b5c3a81876e4760befd3dcac6aa143acb2c3090915a05996fec2f
+size 4964

runs/Feb26_18-51-14_sanchit--v100/events.out.tfevents.1645901511.sanchit--v100.205521.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94cc2cb481b6caa15debb70f4cdb948946b55f5575b8affc035b690a59d96a3d
+size 40188

runs/Feb26_19-49-14_sanchit--v100/1645904992.6813512/events.out.tfevents.1645904992.sanchit--v100.205663.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8d9f46c2b9627f33de409dfde09a8ec8a4a56b9ac22437a302868b03711c914
+size 4964

runs/Feb26_19-49-14_sanchit--v100/events.out.tfevents.1645904992.sanchit--v100.205663.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde97c05d5c122b5aaed96f9846d947751ec9a6e6e213eb0e6eb5ba48507a4ce
+size 9169

runs/Feb26_19-50-30_sanchit--v100/1645905067.4466424/events.out.tfevents.1645905067.sanchit--v100.205784.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe5e75e621cbb680ee2dbfda7b3f2fb1a7daa76b089c9e6d0771e28b234ea60
+size 4964

runs/Feb26_19-50-30_sanchit--v100/events.out.tfevents.1645905067.sanchit--v100.205784.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7a64f9eb3a0150b8a3d75d7780ddf237ba3a65e8e77ad26b09159c2029f6e3
+size 9169

runs/Feb26_19-51-46_sanchit--v100/1645905142.727175/events.out.tfevents.1645905142.sanchit--v100.205904.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f884ced64819e2fcf0f6300e809ed57910bee28ddd490c21535de93036d170
+size 4964

runs/Feb26_19-51-46_sanchit--v100/events.out.tfevents.1645905142.sanchit--v100.205904.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd96d3297d5d7e6dee4148abb9aa9b41ef04969bcbfbf9781a1abb14020c699d
+size 9169

runs/Mar06_15-45-07_sanchit--v100/1646581547.3006496/events.out.tfevents.1646581547.sanchit--v100.289548.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6192400c45b6052858f5629ef7e37cf7a5a1fd250a0938252fa16c48c25e3576
+size 4973

runs/Mar06_15-45-07_sanchit--v100/events.out.tfevents.1646581547.sanchit--v100.289548.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:744ea58aaac38b077db7e5516c20f4a01e496d80f8c33dcbfe8ec8f1bc85f4c8
+size 401622

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:833b5cd314bea40a76dbec2a446525f4ffb48ad04d67b0a30a8e18ce88792530
+oid sha256:cbf05b39fa8503875b25388425a2370c7a9ec2c9bc2452f73cf2662466f2027f
 size 3119

wandb/debug-internal.log

@@ -0,0 +1 @@
+run-20220306_154547-4pqitlp3/logs/debug-internal.log

wandb/debug.log

@@ -0,0 +1 @@
+run-20220306_154547-4pqitlp3/logs/debug.log

wandb/latest-run

@@ -0,0 +1 @@
+run-20220306_154547-4pqitlp3

wandb/run-20220306_154547-4pqitlp3/files/requirements.txt

@@ -0,0 +1,184 @@
+absl-py==1.0.0
+aiohttp==3.8.1
+aiosignal==1.2.0
+anyio==3.5.0
+appdirs==1.4.4
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+asttokens==2.0.5
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+babel==2.9.1
+backcall==0.2.0
+bitsandbytes-cuda113==0.26.0
+black==22.1.0
+bleach==4.1.0
+cachetools==5.0.0
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.11
+chex==0.1.0
+click==8.0.3
+clldutils==3.10.1
+colorlog==6.6.0
+csvw==1.11.0
+cycler==0.11.0
+datasets==1.18.3
+debugpy==1.5.1
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.4
+dlinfo==1.2.1
+dm-tree==0.1.6
+docker-pycreds==0.4.0
+entrypoints==0.4
+executing==0.8.2
+filelock==3.4.2
+flatbuffers==2.0
+flax==0.4.0
+fonttools==4.29.1
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.27
+google-auth-oauthlib==0.4.6
+google-auth==2.6.0
+grpcio==1.43.0
+huggingface-hub==0.4.0
+hypothesis==6.36.1
+idna==3.3
+importlib-metadata==4.10.1
+ipykernel==6.8.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.5
+isodate==0.6.1
+jax==0.2.28
+jaxlib==0.1.76+cuda11.cudnn82
+jedi==0.18.1
+jinja2==3.0.3
+jiwer==2.3.0
+joblib==1.1.0
+json5==0.9.6
+jsonschema==4.4.0
+jupyter-client==7.1.2
+jupyter-console==6.4.0
+jupyter-core==4.9.1
+jupyter-server==1.13.5
+jupyter==1.0.0
+jupyterlab-pygments==0.1.2
+jupyterlab-server==2.10.3
+jupyterlab-widgets==1.0.2
+jupyterlab==3.2.9
+kiwisolver==1.3.2
+librosa==0.8.1
+llvmlite==0.38.0
+markdown==3.3.6
+markupsafe==2.0.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mistune==0.8.4
+msgpack==1.0.3
+multidict==6.0.2
+multiprocess==0.70.12.2
+mypy-extensions==0.4.3
+nbclassic==0.3.5
+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==1.21.5
+oauthlib==3.2.0
+opt-einsum==3.3.0
+optax==0.1.0
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+parso==0.8.3
+pathspec==0.9.0
+pathtools==0.1.2
+pexpect==4.8.0
+phonemizer==3.0.1
+pickleshare==0.7.5
+pillow==9.0.0
+pip==22.0.2
+pkg-resources==0.0.0
+platformdirs==2.4.1
+pooch==1.6.0
+prometheus-client==0.13.1
+promise==2.3
+prompt-toolkit==3.0.26
+protobuf==3.19.4
+psutil==5.9.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==6.0.1
+pyasn1-modules==0.2.8
+pyasn1==0.4.8
+pycparser==2.21
+pyctcdecode==0.3.0
+pygments==2.11.2
+pygtrie==2.4.2
+pyparsing==3.0.7
+pyrsistent==0.18.1
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+pytz==2021.3
+pyyaml==6.0
+pyzmq==22.3.0
+qtconsole==5.2.2
+qtpy==2.0.1
+regex==2022.1.18
+requests-oauthlib==1.3.1
+requests==2.27.1
+resampy==0.2.2
+rfc3986==2.0.0
+rsa==4.8
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+segments==2.2.0
+send2trash==1.8.0
+sentry-sdk==1.5.6
+setuptools==44.1.1
+shortuuid==1.0.8
+six==1.16.0
+smmap==5.0.0
+sniffio==1.2.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+stack-data==0.1.4
+tabulate==0.8.9
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorboard==2.8.0
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+threadpoolctl==3.1.0
+tokenizers==0.11.4
+tomli==2.0.0
+toolz==0.11.2
+torch==1.10.2+cu113
+torchaudio==0.10.2+cu113
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.17.0.dev0
+typing-extensions==3.10.0.2
+uritemplate==4.1.1
+urllib3==1.26.8
+wandb==0.12.10
+wcwidth==0.2.5
+webencodings==0.5.1
+websocket-client==1.2.3
+werkzeug==2.0.2
+wheel==0.37.1
+widgetsnbextension==3.5.2
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220306_154547-4pqitlp3/files/wandb-metadata.json

@@ -0,0 +1,59 @@
+{
+    "os": "Linux-5.11.0-1028-gcp-x86_64-with-glibc2.33",
+    "python": "3.9.5",
+    "heartbeatAt": "2022-03-06T15:45:48.785023",
+    "startedAt": "2022-03-06T15:45:47.681183",
+    "docker": null,
+    "gpu": "Tesla V100-SXM2-16GB",
+    "gpu_count": 2,
+    "cpu_count": 16,
+    "cuda": null,
+    "args": [
+        "--dataset_name=librispeech_asr",
+        "--model_name_or_path=./",
+        "--tokenizer_name=./",
+        "--dataset_config_name=clean",
+        "--train_split_name=train.100",
+        "--eval_split_name=validation",
+        "--output_dir=./",
+        "--preprocessing_num_workers=1",
+        "--length_column_name=input_length",
+        "--overwrite_output_dir",
+        "--num_train_epochs=20",
+        "--per_device_train_batch_size=8",
+        "--per_device_eval_batch_size=8",
+        "--gradient_accumulation_steps=4",
+        "--generation_max_length=40",
+        "--generation_num_beams=1",
+        "--learning_rate=1e-4",
+        "--warmup_steps=1000",
+        "--evaluation_strategy=steps",
+        "--text_column_name=text",
+        "--save_steps=2500",
+        "--eval_steps=2500",
+        "--logging_steps=1",
+        "--save_total_limit=1",
+        "--freeze_feature_encoder",
+        "--gradient_checkpointing",
+        "--fp16",
+        "--group_by_length",
+        "--predict_with_generate",
+        "--do_lower_case",
+        "--do_eval",
+        "--do_train",
+        "--push_to_hub",
+        "--use_auth_token"
+    ],
+    "state": "running",
+    "program": "/home/sanchit_huggingface_co/wav2vec2-2-gpt2-grid-search/run_speech_recognition_seq2seq.py",
+    "codePath": "run_speech_recognition_seq2seq.py",
+    "git": {
+        "remote": "https://huggingface.co/sanchit-gandhi/wav2vec2-2-gpt2-grid-search",
+        "commit": "1be04f97a3f50c64a680b1921fe6f4e9dca6a92a"
+    },
+    "email": "sanchit@huggingface.co",
+    "root": "/home/sanchit_huggingface_co/wav2vec2-2-gpt2-grid-search",
+    "host": "sanchit--v100",
+    "username": "sanchit_huggingface_co",
+    "executable": "/home/sanchit_huggingface_co/gcp/bin/python"
+}

wandb/run-20220306_154547-4pqitlp3/logs/debug.log

@@ -0,0 +1,27 @@
+2022-03-06 15:45:47,682 INFO    MainThread:289548 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/wav2vec2-2-gpt2-grid-search/wandb/settings
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_setup.py:_flush():75] Loading settings from environment variables: {}
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_setup.py:_flush():75] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_seq2seq.py', 'program': '/home/sanchit_huggingface_co/wav2vec2-2-gpt2-grid-search/run_speech_recognition_seq2seq.py'}
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/wav2vec2-2-gpt2-grid-search/wandb/run-20220306_154547-4pqitlp3/logs/debug.log
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/wav2vec2-2-gpt2-grid-search/wandb/run-20220306_154547-4pqitlp3/logs/debug-internal.log
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_init.py:init():420] calling init triggers
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_init.py:init():425] wandb.init called with sweep_config: {}
+config: {}
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [wandb_init.py:init():471] starting backend
+2022-03-06 15:45:47,683 INFO    MainThread:289548 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-03-06 15:45:47,745 INFO    MainThread:289548 [backend.py:ensure_launched():219] starting backend process...
+2022-03-06 15:45:47,807 INFO    MainThread:289548 [backend.py:ensure_launched():224] started backend process with pid: 289650
+2022-03-06 15:45:47,809 INFO    MainThread:289548 [wandb_init.py:init():480] backend started and connected
+2022-03-06 15:45:47,819 INFO    MainThread:289548 [wandb_init.py:init():550] updated telemetry
+2022-03-06 15:45:47,971 INFO    MainThread:289548 [wandb_init.py:init():581] communicating current version
+2022-03-06 15:45:48,684 INFO    MainThread:289548 [wandb_init.py:init():586] got version response upgrade_message: "wandb version 0.12.11 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2022-03-06 15:45:48,684 INFO    MainThread:289548 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
+2022-03-06 15:45:48,779 INFO    MainThread:289548 [wandb_init.py:init():624] starting run threads in backend
+2022-03-06 15:45:48,887 INFO    MainThread:289548 [wandb_run.py:_console_start():1827] atexit reg
+2022-03-06 15:45:48,887 INFO    MainThread:289548 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
+2022-03-06 15:45:48,888 INFO    MainThread:289548 [wandb_run.py:_redirect():1706] Redirecting console.
+2022-03-06 15:45:48,889 INFO    MainThread:289548 [wandb_run.py:_redirect():1762] Redirects installed.
+2022-03-06 15:45:48,889 INFO    MainThread:289548 [wandb_init.py:init():651] run started, returning control to user process
+2022-03-06 15:45:48,892 INFO    MainThread:289548 [wandb_run.py:_config_callback():966] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 50, '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': ['SpeechEncoderDecoderModel'], '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': None, 'pad_token_id': 50256, 'eos_token_id': 50256, 'sep_token_id': None, 'decoder_start_token_id': 50256, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50257, 'n_positions': 1024, 'n_embd': 1024, 'n_layer': 24, 'n_head': 16, 'n_inner': None, 'activation_function': 'gelu_new', 'resid_pdrop': 0.0, 'embd_pdrop': 0.0, 'attn_pdrop': 0.0, 'layer_norm_epsilon': 1e-05, 'initializer_range': 0.02, 'summary_type': 'cls_index', 'summary_use_proj': True, 'summary_activation': None, 'summary_first_dropout': 0.0, 'summary_proj_to_labels': True, 'scale_attn_weights': True, 'use_cache': False, 'scale_attn_by_inverse_layer_idx': False, 'reorder_and_upcast_attn': False, 'bos_token_id': 50256, 'eos_token_id': 50256, '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': True, 'cross_attention_hidden_size': None, 'add_cross_attention': True, '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': ['GPT2LMHeadModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'pad_token_id': None, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': {'text-generation': {'do_sample': True, 'max_length': 50}}, 'problem_type': None, '_name_or_path': 'gpt2-medium', 'transformers_version': '4.17.0.dev0', 'n_ctx': 1024, 'n_special': 0, 'predict_special_tokens': True, 'model_type': 'gpt2'}, 'encoder': {'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': 0, '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-large-lv60', 'transformers_version': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, 'hidden_dropout_prob': 0.0, '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': 0.0, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': False, 'mask_time_prob': 0.0, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, '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': 'sum', 'ctc_zero_infinity': False, 'add_adapter': True, '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, 'model_type': 'wav2vec2'}, 'model_type': 'speech-encoder-decoder', 'processor_class': 'Wav2Vec2Processor', 'use_cache': False, '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': 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': 20.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 1000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Mar06_15-45-07_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 1, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 2500, 'save_total_limit': 1, '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': 2500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', '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': "['tensorboard', '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': '', 'sortish_sampler': False, 'predict_with_generate': True, 'generation_max_length': 40, 'generation_num_beams': 1, 'train_batch_size': 8, 'eval_batch_size': 8}
+2022-03-06 15:45:48,894 INFO    MainThread:289548 [wandb_watch.py:watch():43] Watching

wandb/run-20220306_154547-4pqitlp3/run-4pqitlp3.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:304850472f5a91b3eb595f2daa598b619d43b325ef5b2d166a5319b9fe821b70
+size 154719280