Training in progress, step 500

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa56856a1acd2d7e9dd4e73ae576f4b2abda18452449998a1fb288827accbd64
+oid sha256:eff38200325c04ab1571edd60d279a85085e529b2ee62bc95a2fcb8cb21d8dbc
 size 1262083569

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1026f32f958f90cabec077c68bf3d1930fa69c114d65dc0a79e3c7e322a787e
+oid sha256:2d1df92319f113f5c8e9351655b7b394f03cfde64572411bd15fe44a33d3ca39
 size 3055

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220129_182318-2mzfaga3/logs/debug-internal.log
+run-20220130_021614-39ybnrhl/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220129_182318-2mzfaga3/logs/debug.log
+run-20220130_021614-39ybnrhl/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220129_182318-2mzfaga3
+run-20220130_021614-39ybnrhl

wandb/run-20220129_182318-2mzfaga3/files/output.log

@@ -1094,3 +1094,290 @@ Configuration saved in ./checkpoint-1000/config.json
 {'eval_loss': 0.41906237602233887, 'eval_wer': 0.40979955456570155, 'eval_runtime': 138.3475, 'eval_samples_per_second': 18.858, 'eval_steps_per_second': 0.267, 'epoch': 25.0}
 Model weights saved in ./checkpoint-1000/pytorch_model.bin
 Configuration saved in ./checkpoint-1000/preprocessor_config.json
+Configuration saved in ./preprocessor_config.json
+Deleting older checkpoint [checkpoint-500] due to args.save_total_limit
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 27%|█████████████████████████████████████████████▎                                                                                                                       | 1099/4000 [2:45:46<7:14:23,  8.98s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 30%|█████████████████████████████████████████████████▍                                                                                                                   | 1199/4000 [3:00:08<6:16:39,  8.07s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+

wandb/run-20220130_021614-39ybnrhl/files/output.log

@@ -0,0 +1,549 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  2%|████▏                                                                                                                                                                    | 99/4000 [14:10<9:36:45,  8.87s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  5%|████████▎                                                                                                                                                               | 199/4000 [28:12<8:13:59,  7.80s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+  7%|████████████▌                                                                                                                                                           | 299/4000 [42:21<8:56:05,  8.69s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 10%|████████████████▊                                                                                                                                                       | 399/4000 [56:27<8:01:57,  8.03s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 12%|████████████████████▊                                                                                                                                                 | 500/4000 [1:10:43<9:43:01,  9.99s/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 = 2609
+  Batch size = 72
+{'loss': 0.3382, 'learning_rate': 0.000998, 'epoch': 12.5}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 37/37 [02:05<00:00,  1.94s/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_021614-39ybnrhl/files/requirements.txt

@@ -0,0 +1,87 @@
+aiohttp==3.8.1
+aiosignal==1.2.0
+appdirs==1.4.4
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+bitsandbytes-cuda113==0.26.0
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.10
+click==8.0.3
+clldutils==3.10.1
+colorlog==6.6.0
+configparser==5.2.0
+csvw==1.11.0
+datasets==1.18.1.dev0
+decorator==5.1.1
+dill==0.3.4
+dlinfo==1.2.1
+docker-pycreds==0.4.0
+filelock==3.4.2
+frozenlist==1.3.0
+fsspec==2022.1.0
+gitdb==4.0.9
+gitpython==3.1.26
+huggingface-hub==0.4.0
+hypothesis==6.36.0
+idna==3.3
+isodate==0.6.1
+jiwer==2.3.0
+joblib==1.1.0
+librosa==0.8.1
+llvmlite==0.38.0
+multidict==6.0.2
+multiprocess==0.70.12.2
+numba==0.55.0
+numpy==1.21.5
+packaging==21.3
+pandas==1.4.0
+pathtools==0.1.2
+phonemizer==3.0.1
+pip==21.3.1
+pooch==1.6.0
+promise==2.3
+protobuf==3.19.3
+psutil==5.9.0
+pyarrow==6.0.1
+pycparser==2.21
+pyctcdecode==0.3.0
+pygtrie==2.4.2
+pyparsing==3.0.7
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+pytz==2021.3
+pyyaml==6.0
+regex==2022.1.18
+requests==2.27.1
+resampy==0.2.2
+rfc3986==2.0.0
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+segments==2.2.0
+sentry-sdk==1.5.4
+setuptools==60.2.0
+shortuuid==1.0.8
+six==1.16.0
+smmap==5.0.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+subprocess32==3.5.4
+tabulate==0.8.9
+termcolor==1.1.0
+threadpoolctl==3.0.0
+tokenizers==0.11.4
+torch==1.10.1
+torchaudio==0.10.1
+tqdm==4.62.3
+transformers==4.16.0.dev0
+typing-extensions==4.0.1
+uritemplate==4.1.1
+urllib3==1.26.8
+wandb==0.12.9
+wheel==0.37.1
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0

wandb/run-20220130_021614-39ybnrhl/files/wandb-metadata.json

@@ -0,0 +1,76 @@
+{
+    "os": "Linux-4.18.0-305.10.2.el8_4.x86_64-x86_64-with-glibc2.28",
+    "python": "3.9.6",
+    "heartbeatAt": "2022-01-30T07:16:15.886605",
+    "startedAt": "2022-01-30T07:16:14.884589",
+    "docker": null,
+    "gpu": "Tesla V100-PCIE-32GB",
+    "gpu_count": 3,
+    "cpu_count": 64,
+    "cuda": null,
+    "args": [
+        "--dataset_name=mozilla-foundation/common_voice_7_0",
+        "--model_name_or_path=facebook/wav2vec2-xls-r-300m",
+        "--dataset_config_name=et",
+        "--output_dir=./",
+        "--overwrite_output_dir",
+        "--num_train_epochs=100",
+        "--per_device_train_batch_size=72",
+        "--per_device_eval_batch_size=72",
+        "--gradient_accumulation_steps=2",
+        "--learning_rate=3e-4",
+        "--save_total_limit=1",
+        "--warmup_steps=500",
+        "--evaluation_strategy=steps",
+        "--text_column_name=sentence",
+        "--length_column_name=input_length",
+        "--save_steps=500",
+        "--eval_steps=500",
+        "--logging_steps=100",
+        "--layerdrop=0.0",
+        "--freeze_feature_encoder",
+        "--feat_proj_dropout=0.1",
+        "--chars_to_ignore",
+        ",",
+        "?",
+        ".",
+        "!",
+        "-",
+        ";",
+        ":",
+        "\"",
+        "\u201c",
+        "%",
+        "\u2018",
+        "\u201d",
+        "\ufffd",
+        "\u2014",
+        "\u2019",
+        "\u2026",
+        "\u2013",
+        "--gradient_checkpointing",
+        "--lr_scheduler_type=cosine",
+        "--fp16",
+        "--group_by_length",
+        "--mask_time_prob=0.1",
+        "--mask_time_length=10",
+        "--report_to=wandb",
+        "--run_name=cosine+drop_proj+low_specaugment-300M",
+        "--do_train",
+        "--do_eval",
+        "--use_auth_token",
+        "--push_to_hub"
+    ],
+    "state": "running",
+    "program": "/home/sagrilaft/Project/audio/xls-r-et/src/run_speech_recognition_ctc_bnb.py",
+    "codePath": "src/run_speech_recognition_ctc_bnb.py",
+    "git": {
+        "remote": "https://huggingface.co/shpotes/xls-r-et",
+        "commit": "8495b6d98c0b67cc7364e72489f3bebc21b0d023"
+    },
+    "email": "[email protected]",
+    "root": "/home/sagrilaft/Project/audio/xls-r-et",
+    "host": "ganymede.eafit.edu.co",
+    "username": "sagrilaft",
+    "executable": "/home/sagrilaft/Project/audio/xls-r-et/.venv/bin/python"
+}

wandb/run-20220130_021614-39ybnrhl/logs/debug.log

@@ -0,0 +1,24 @@
+2022-01-30 02:16:14,887 INFO    MainThread:2586598 [wandb_setup.py:_flush():71] setting env: {'project': 'xls-r-estonian'}
+2022-01-30 02:16:14,887 INFO    MainThread:2586598 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-01-30 02:16:14,888 INFO    MainThread:2586598 [wandb_init.py:_log_setup():371] Logging user logs to /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220130_021614-39ybnrhl/logs/debug.log
+2022-01-30 02:16:14,888 INFO    MainThread:2586598 [wandb_init.py:_log_setup():372] Logging internal logs to /home/sagrilaft/Project/audio/xls-r-et/wandb/run-20220130_021614-39ybnrhl/logs/debug-internal.log
+2022-01-30 02:16:14,888 INFO    MainThread:2586598 [wandb_init.py:init():404] calling init triggers
+2022-01-30 02:16:14,889 INFO    MainThread:2586598 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+config: {}
+2022-01-30 02:16:14,889 INFO    MainThread:2586598 [wandb_init.py:init():460] starting backend
+2022-01-30 02:16:14,889 INFO    MainThread:2586598 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-01-30 02:16:14,926 INFO    MainThread:2586598 [backend.py:ensure_launched():216] starting backend process...
+2022-01-30 02:16:14,954 INFO    MainThread:2586598 [backend.py:ensure_launched():221] started backend process with pid: 2586828
+2022-01-30 02:16:14,956 INFO    MainThread:2586598 [wandb_init.py:init():469] backend started and connected
+2022-01-30 02:16:14,963 INFO    MainThread:2586598 [wandb_init.py:init():533] updated telemetry
+2022-01-30 02:16:15,032 INFO    MainThread:2586598 [wandb_init.py:init():563] communicating current version
+2022-01-30 02:16:15,686 INFO    MainThread:2586598 [wandb_init.py:init():568] got version response 
+2022-01-30 02:16:15,687 INFO    MainThread:2586598 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-01-30 02:16:15,878 INFO    MainThread:2586598 [wandb_init.py:init():606] starting run threads in backend
+2022-01-30 02:16:15,927 INFO    MainThread:2586598 [wandb_run.py:_console_start():1810] atexit reg
+2022-01-30 02:16:15,928 INFO    MainThread:2586598 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-01-30 02:16:15,929 INFO    MainThread:2586598 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-01-30 02:16:15,932 INFO    MainThread:2586598 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-01-30 02:16:15,933 INFO    MainThread:2586598 [wandb_init.py:init():633] run started, returning control to user process
+2022-01-30 02:16:15,950 INFO    MainThread:2586598 [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': 36, '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': '4.16.0.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': 0.0, 'feat_proj_dropout': 0.1, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 39, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, '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': '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': 72, 'per_device_eval_batch_size': 72, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0003, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 100.0, 'max_steps': -1, 'lr_scheduler_type': 'cosine', 'warmup_ratio': 0.0, 'warmup_steps': 500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Jan30_02-15-54_ganymede.eafit.edu.co', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, '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': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'cosine+drop_proj+low_specaugment-300M', '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': 72, 'eval_batch_size': 72}
+2022-01-30 02:16:15,953 INFO    MainThread:2586598 [wandb_watch.py:watch():43] Watching