Training in progress, step 133000

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43671ed5bafa71795f59db895d95766f46f99de869a3f313e49390f7014d06c1
+oid sha256:54679ac59e7623fbda9543030f346a174ef73ffeb3d08f1c6e4b2bdc00c09118
 size 1262066801

run.sh

@@ -2,7 +2,6 @@ WANDB_ENTITY=NbAiLab WANDB_PROJECT=wav2vec2 python run_speech_recognition_ctc.py
         --model_name_or_path="chcaa/xls-r-300m-danish" \
         --hub_model_id="NbAiLab/wav2vec2-large-danish-npsc-nst" \
         --output_dir="./" \
-        --overwrite_output_dir \
         --num_train_epochs="15" \
         --per_device_train_batch_size="16" \
         --per_device_eval_batch_size="16" \

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}]}
+{"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}]}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871d12761c34d34a636889262bf1872352c2b2442764aa917c8b73fdf8b937e2
+oid sha256:0dd5fb4be5c6c121f2596e50e61754ab6a9a374bb3b5c2443a64880e1cf7dc7c
 size 3055

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220819_142520-3s4zhm8g/logs/debug-internal.log
+run-20220829_113057-2w833bqu/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220819_142520-3s4zhm8g/logs/debug.log
+run-20220829_113057-2w833bqu/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220819_142520-3s4zhm8g
+run-20220829_113057-2w833bqu

wandb/run-20220819_142520-3s4zhm8g/logs/debug.log

@@ -25,3 +25,5 @@ config: {}
 2022-08-19 14:25:22,084 INFO    MainThread:3283921 [wandb_init.py:init():684] run started, returning control to user process
 2022-08-19 14:25:22,106 INFO    MainThread:3283921 [wandb_run.py:_config_callback():1131] 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, 'typical_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, 'exponential_decay_length_penalty': None, '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': 38, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'chcaa/xls-r-300m-danish', 'transformers_version': '4.18.0', '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': 0.047, 'attention_dropout': 0.094, 'activation_dropout': 0.055, 'feat_proj_dropout': 0.04, 'final_dropout': 0.0, 'layerdrop': 0.041, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 41, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.082, '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': True, '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': 16, 'per_device_eval_batch_size': 16, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'eval_delay': 0, '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': 15.0, '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/Aug19_14-24-25_dante', '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, 'data_seed': 'None', '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': './', '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': 'NbAiLab/wav2vec2-large-danish-npsc-nst', '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': 16, 'eval_batch_size': 16}
 2022-08-19 14:25:22,109 INFO    MainThread:3283921 [wandb_watch.py:watch():47] Watching
+2022-08-28 17:57:18,423 INFO    MainThread:3283921 [wandb_run.py:_atexit_cleanup():1866] got exitcode: 1
+2022-08-28 17:57:18,425 INFO    MainThread:3283921 [wandb_run.py:_restore():1838] restore

wandb/run-20220829_113057-2w833bqu/files/output.log

@@ -0,0 +1,1278 @@
+
+  0%|                                                                                                                                                                                                                                                  | 0/142305 [00:00<?, ?it/s]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▋               | 132600/142305 [2:19:44<5:22:02,  1.99s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▊               | 132699/142305 [2:22:36<5:32:43,  2.08s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉               | 132800/142305 [2:25:30<4:34:00,  1.73s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ 93%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▏              | 132899/142305 [2:28:21<3:45:33,  1.44s/it]
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+***** Running Evaluation *****█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎              | 133000/142305 [2:31:15<3:32:12,  1.37s/it]
+  Num examples = 40498
+  Batch size = 16
+{'loss': 0.0921, 'learning_rate': 6.667616977299455e-06, 'epoch': 14.02}
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▉| 2531/2532 [30:30<00:00,  1.49it/s]
+Saving model checkpoint to ./checkpoint-133000
+Configuration saved in ./checkpoint-133000/config.json█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▎              | 133000/142305 [3:02:34<3:32:12,  1.37s/it]
+Model weights saved in ./checkpoint-133000/pytorch_model.bin
+Feature extractor saved in ./checkpoint-133000/preprocessor_config.json

wandb/run-20220829_113057-2w833bqu/files/requirements.txt

@@ -0,0 +1,77 @@
+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
+certifi==2021.10.8
+cffi==1.15.0
+charset-normalizer==2.0.12
+click==8.1.2
+datasets==2.1.0
+decorator==5.1.1
+dill==0.3.4
+docker-pycreds==0.4.0
+filelock==3.6.0
+frozenlist==1.3.0
+fsspec==2022.3.0
+gitdb==4.0.9
+gitpython==3.1.27
+huggingface-hub==0.5.1
+hypothesis==6.46.5
+idna==3.3
+jiwer==2.3.0
+joblib==1.1.0
+kenlm==0.0.0
+librosa==0.9.1
+llvmlite==0.38.0
+multidict==6.0.2
+multiprocess==0.70.12.2
+numba==0.55.1
+numpy==1.21.6
+packaging==21.3
+pandas==1.4.2
+pathtools==0.1.2
+pillow==9.1.0
+pip==20.3.4
+pkg-resources==0.0.0
+pooch==1.6.0
+promise==2.3
+protobuf==3.20.1
+psutil==5.9.0
+pyarrow==7.0.0
+pycparser==2.21
+pyctcdecode==0.3.0
+pygtrie==2.4.2
+pyparsing==3.0.8
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+pytz==2022.1
+pyyaml==6.0
+regex==2022.4.24
+requests==2.27.1
+resampy==0.2.2
+responses==0.18.0
+sacremoses==0.0.49
+scikit-learn==1.0.2
+scipy==1.8.0
+sentry-sdk==1.5.10
+setproctitle==1.2.3
+setuptools==44.1.1
+shortuuid==1.0.8
+six==1.16.0
+smmap==5.0.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+threadpoolctl==3.1.0
+tokenizers==0.12.1
+torch==1.11.0+cu113
+torchaudio==0.11.0+cu113
+torchvision==0.12.0+cu113
+tqdm==4.64.0
+transformers==4.18.0
+typing-extensions==4.2.0
+urllib3==1.26.9
+wandb==0.12.15
+xxhash==3.0.0
+yarl==1.7.2

wandb/run-20220829_113057-2w833bqu/files/wandb-metadata.json

@@ -0,0 +1,61 @@
+{
+    "os": "Linux-5.13.0-40-generic-x86_64-with-glibc2.34",
+    "python": "3.9.7",
+    "heartbeatAt": "2022-08-29T09:30:59.050051",
+    "startedAt": "2022-08-29T09:30:57.965174",
+    "docker": null,
+    "cpu_count": 96,
+    "cuda": null,
+    "args": [
+        "--model_name_or_path=chcaa/xls-r-300m-danish",
+        "--hub_model_id=NbAiLab/wav2vec2-large-danish-npsc-nst",
+        "--output_dir=./",
+        "--num_train_epochs=15",
+        "--per_device_train_batch_size=16",
+        "--per_device_eval_batch_size=16",
+        "--gradient_accumulation_steps=2",
+        "--learning_rate=1e-4",
+        "--warmup_steps=2000",
+        "--length_column_name=input_length",
+        "--evaluation_strategy=steps",
+        "--text_column_name=text",
+        "--save_steps=500",
+        "--eval_steps=500",
+        "--logging_steps=100",
+        "--layerdrop=0.041",
+        "--attention_dropout=0.094",
+        "--activation_dropout=0.055",
+        "--hidden_dropout=0.047",
+        "--save_total_limit=3",
+        "--freeze_feature_encoder",
+        "--feat_proj_dropout=0.04",
+        "--mask_time_prob=0.082",
+        "--mask_time_length=10",
+        "--mask_feature_prob=0.25",
+        "--mask_feature_length=64",
+        "--gradient_checkpointing",
+        "--min_duration_in_seconds=0.5",
+        "--max_duration_in_seconds=20.0",
+        "--use_auth_token",
+        "--seed=42",
+        "--fp16",
+        "--group_by_length",
+        "--do_train",
+        "--do_eval",
+        "--push_to_hub",
+        "--preprocessing_num_workers=32",
+        "--ctc_zero_infinity"
+    ],
+    "state": "running",
+    "program": "/mnt/lv_ai_1_dante/ml/models/wav2vec2-large-danish-npsc-nst/run_speech_recognition_ctc.py",
+    "codePath": "run_speech_recognition_ctc.py",
+    "git": {
+        "remote": "https://huggingface.co/NbAiLab/wav2vec2-large-danish-npsc-nst",
+        "commit": "10aa498e9c5a43a60bca2edce8483e8b1304f03d"
+    },
+    "email": "rolv_arild@hotmail.com",
+    "root": "/mnt/lv_ai_1_dante/ml/models/wav2vec2-large-danish-npsc-nst",
+    "host": "dante",
+    "username": "rolvb",
+    "executable": "/mnt/lv_ai_1_dante/ml/rolvb/venv/bin/python"
+}

wandb/run-20220829_113057-2w833bqu/logs/debug.log

@@ -0,0 +1,27 @@
+2022-08-29 11:30:57,968 INFO    MainThread:2612000 [wandb_setup.py:_flush():75] Loading settings from /home/rolvb/.config/wandb/settings
+2022-08-29 11:30:57,968 INFO    MainThread:2612000 [wandb_setup.py:_flush():75] Loading settings from /mnt/lv_ai_1_dante/ml/models/wav2vec2-large-danish-npsc-nst/wandb/settings
+2022-08-29 11:30:57,968 INFO    MainThread:2612000 [wandb_setup.py:_flush():75] Loading settings from environment variables: {'project': 'wav2vec2', 'entity': 'NbAiLab'}
+2022-08-29 11:30:57,968 INFO    MainThread:2612000 [wandb_setup.py:_flush():75] Inferring run settings from compute environment: {'program_relpath': 'run_speech_recognition_ctc.py', 'program': '/mnt/lv_ai_1_dante/ml/models/wav2vec2-large-danish-npsc-nst/run_speech_recognition_ctc.py'}
+2022-08-29 11:30:57,969 INFO    MainThread:2612000 [wandb_init.py:_log_setup():437] Logging user logs to /mnt/lv_ai_1_dante/ml/models/wav2vec2-large-danish-npsc-nst/wandb/run-20220829_113057-2w833bqu/logs/debug.log
+2022-08-29 11:30:57,969 INFO    MainThread:2612000 [wandb_init.py:_log_setup():438] Logging internal logs to /mnt/lv_ai_1_dante/ml/models/wav2vec2-large-danish-npsc-nst/wandb/run-20220829_113057-2w833bqu/logs/debug-internal.log
+2022-08-29 11:30:57,969 INFO    MainThread:2612000 [wandb_init.py:init():471] calling init triggers
+2022-08-29 11:30:57,969 INFO    MainThread:2612000 [wandb_init.py:init():474] wandb.init called with sweep_config: {}
+config: {}
+2022-08-29 11:30:57,969 INFO    MainThread:2612000 [wandb_init.py:init():524] starting backend
+2022-08-29 11:30:57,970 INFO    MainThread:2612000 [backend.py:_multiprocessing_setup():97] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-08-29 11:30:58,059 INFO    MainThread:2612000 [backend.py:ensure_launched():217] starting backend process...
+2022-08-29 11:30:58,126 INFO    MainThread:2612000 [backend.py:ensure_launched():222] started backend process with pid: 2612775
+2022-08-29 11:30:58,127 INFO    MainThread:2612000 [wandb_init.py:init():533] backend started and connected
+2022-08-29 11:30:58,136 INFO    MainThread:2612000 [wandb_init.py:init():597] updated telemetry
+2022-08-29 11:30:58,300 INFO    MainThread:2612000 [wandb_init.py:init():628] communicating run to backend with 30 second timeout
+2022-08-29 11:30:58,888 INFO    MainThread:2612000 [wandb_run.py:_on_init():1923] communicating current version
+2022-08-29 11:30:59,031 INFO    MainThread:2612000 [wandb_run.py:_on_init():1927] got version response upgrade_message: "wandb version 0.13.2 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2022-08-29 11:30:59,031 INFO    MainThread:2612000 [wandb_init.py:init():659] starting run threads in backend
+2022-08-29 11:30:59,082 INFO    MainThread:2612000 [wandb_run.py:_console_start():1897] atexit reg
+2022-08-29 11:30:59,083 INFO    MainThread:2612000 [wandb_run.py:_redirect():1770] redirect: SettingsConsole.REDIRECT
+2022-08-29 11:30:59,084 INFO    MainThread:2612000 [wandb_run.py:_redirect():1775] Redirecting console.
+2022-08-29 11:30:59,086 INFO    MainThread:2612000 [wandb_run.py:_redirect():1831] Redirects installed.
+2022-08-29 11:30:59,087 INFO    MainThread:2612000 [wandb_init.py:init():684] run started, returning control to user process
+2022-08-29 11:30:59,112 INFO    MainThread:2612000 [wandb_run.py:_config_callback():1131] 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, 'typical_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, 'exponential_decay_length_penalty': None, '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': 38, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'chcaa/xls-r-300m-danish', 'transformers_version': '4.18.0', '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': 0.047, 'attention_dropout': 0.094, 'activation_dropout': 0.055, 'feat_proj_dropout': 0.04, 'final_dropout': 0.0, 'layerdrop': 0.041, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 41, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.082, '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': True, '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': False, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 16, 'per_device_eval_batch_size': 16, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 2, 'eval_accumulation_steps': 'None', 'eval_delay': 0, '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': 15.0, '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/Aug29_11-30-20_dante', '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, 'data_seed': 'None', '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': './', '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': 'NbAiLab/wav2vec2-large-danish-npsc-nst', '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': 16, 'eval_batch_size': 16}
+2022-08-29 11:30:59,115 INFO    MainThread:2612000 [wandb_watch.py:watch():47] Watching

wandb/run-20220829_113057-2w833bqu/run-2w833bqu.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c1bab05ae78428d7305fee15e82ce6544cef06fccc572e83acc3282b02d9bb8
+size 4148267