Model save

config.json

@@ -182,7 +182,7 @@
     "forced_eos_token_id": null,
     "gradient_checkpointing": false,
     "hidden_act": "gelu",
-    "hidden_dropout": 0.035938233699532036,
+    "hidden_dropout": 0.18004101365999406,
     "hidden_size": 1024,
     "id2label": {
       "0": "LABEL_0",

emissions.csv

@@ -1,2 +1,3 @@
 timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
 2022-05-05T16:24:44,d1ee5246-da5a-4bbb-a48e-edf347d44452,codecarbon,93789.2286529541,4.4657849913272685,7.885899684491028,USA,USA,Iowa,Y,gcp,us-central1
+2022-05-05T16:37:38,3042b653-af40-4cc1-8eec-061528a59ed7,codecarbon,10.825525283813477,0.00029573218373195776,0.0005222182301464909,USA,USA,Iowa,Y,gcp,us-central1

runs/May05_16-32-27_sanchit--v100/1651768642.7722313/events.out.tfevents.1651768642.sanchit--v100.65172.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fe9010d25b5426ae74e1154e5be2727f4b9d3dc3d3ac8423b4e36ab102ca5b1
+size 5184

runs/May05_16-32-27_sanchit--v100/events.out.tfevents.1651768642.sanchit--v100.65172.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dffb33c2552c28d9cdf40229f277c5ce3d0f56c41496a3ad6c1fcdd0e08ec2d4
+size 10206

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54311328073baaf4c9576b62de98f28bcc986e980c3c849a9409edd618d1e27f
+oid sha256:f53a6a57e9108be1580a99fd7bb15879abb87d024ec5fa14575c3b7fb1db16f0
 size 3247

wandb/debug-cli.log

@@ -80,3 +80,29 @@
 2022-05-05 09:24:03 ERROR {"errors":[{"message":"context deadline exceeded"}]}
 2022-05-05 09:25:36 ERROR 500 response executing GraphQL.
 2022-05-05 09:25:36 ERROR {"errors":[{"message":"context deadline exceeded"}]}
+2022-05-05 16:32:16 INFO Cleaning up finished run: 1tmxz74i
+2022-05-05 16:32:16 INFO Agent received command: run
+2022-05-05 16:32:16 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.18004101365999406
+	language: fr.en
+	learning_rate: 0.0002757119755681108
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./
+	per_device_eval_batch_size: 8
+	per_device_train_batch_size: 8
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-05 16:32:16 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.18004101365999406 --language=fr.en --learning_rate=0.0002757119755681108 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./ --per_device_eval_batch_size=8 --per_device_train_batch_size=8 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-05 16:32:22 INFO Running runs: ['urfp82ib']

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220504_142129-1tmxz74i/logs/debug-internal.log
+run-20220505_163723-urfp82ib/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220504_142129-1tmxz74i/logs/debug.log
+run-20220505_163723-urfp82ib/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220504_142129-1tmxz74i
+run-20220505_163723-urfp82ib

wandb/run-20220504_142129-1tmxz74i/files/config.yaml

@@ -8672,7 +8672,16 @@ _wandb:
       - 5
       - 11
       - 12
+      2:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
       3:
+      - 1
+      - 7
       - 13
       4: 3.9.5
       5: 0.12.10

wandb/run-20220504_142129-1tmxz74i/files/output.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e18202a1774364d9bce0ad6eaa7228beac26c34380f4e6e745afa0fe739feae8
-size 20977130
+oid sha256:1d1786cfcbc8ee6cb2c762b8872e52a8706b47ba5aefb46b3b3e33372a571f67
+size 20996768

wandb/run-20220504_142129-1tmxz74i/logs/debug-internal.log

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91cc8d775a6d70e558fd760ecd96b3f748bd6f4161c4eb4b573a07aa34fe57dc
-size 26053100
+oid sha256:9ca0a284494378c54882b003ce1468e806df7176e30a9d1763d9e6b9d44e52e1
+size 26078926

wandb/run-20220504_142129-1tmxz74i/logs/debug.log

@@ -26,3 +26,165 @@ config: {}
 2022-05-04 14:21:35,284 INFO    MainThread:50375 [wandb_init.py:init():651] run started, returning control to user process
 2022-05-04 14:21:35,288 INFO    MainThread:50375 [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': 40, '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': ['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': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50265, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, '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': True, 'num_beams': 4, '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': 3, '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': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'architectures': ['BartModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'length_penalty': 1.0, 'max_length': 128, 'min_length': 12, 'num_beams': 4}, 'summarization_cnn': {'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'num_beams': 4}, 'summarization_xsum': {'length_penalty': 1.0, 'max_length': 62, 'min_length': 11, 'num_beams': 6}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large', 'transformers_version': '4.19.0.dev0', 'add_bias_logits': False, 'add_final_layer_norm': False, 'classif_dropout': 0.1, 'gradient_checkpointing': False, 'normalize_before': False, 'model_type': 'bart'}, 'encoder': {'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': 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-xls-r-300m', 'transformers_version': '4.19.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, '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': 0.035938233699532036, 'attention_dropout': 0.1, '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': 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': '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, 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'prediction_loss_only': False, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/May04_13-30-37_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_total_limit': 'None', '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, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, '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': 'length', 'report_to': "['tensorboard', 'wandb', 'codecarbon']", '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>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, '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, 'train_batch_size': 8, 'eval_batch_size': 8}
 2022-05-04 14:21:35,292 INFO    MainThread:50375 [wandb_watch.py:watch():43] Watching
+2022-05-05 16:31:21,082 INFO    MainThread:50375 [wandb_run.py:_atexit_cleanup():1797] got exitcode: 1
+2022-05-05 16:31:21,089 INFO    MainThread:50375 [wandb_run.py:_restore():1769] restore
+2022-05-05 16:31:23,715 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 1972
+  total_bytes: 1972
+}
+
+2022-05-05 16:31:23,834 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 1972
+  total_bytes: 1972
+}
+
+2022-05-05 16:31:23,967 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 1972
+  total_bytes: 1972
+}
+
+2022-05-05 16:31:24,862 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 1
+}
+pusher_stats {
+  uploaded_bytes: 1972
+  total_bytes: 1972
+}
+
+2022-05-05 16:31:25,840 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 1972
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:25,942 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 1972
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,045 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 12347603
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,149 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 21261171
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,251 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 21261171
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,354 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 21261171
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,456 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 21261171
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,558 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 21261171
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,660 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 21261171
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,762 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22539656
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,864 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22539656
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:26,966 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22539656
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:27,068 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22539656
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:27,223 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22539656
+  total_bytes: 22539656
+}
+
+2022-05-05 16:31:27,397 INFO    MainThread:50375 [wandb_run.py:_wait_for_finish():1929] got exit ret: done: true
+exit_result {
+}
+file_counts {
+  wandb_count: 5
+}
+pusher_stats {
+  uploaded_bytes: 22539656
+  total_bytes: 22539656
+}
+local_info {
+}
+
+2022-05-05 16:31:29,982 INFO    MainThread:50375 [wandb_run.py:_append_history():2144] rendering history
+2022-05-05 16:31:29,983 INFO    MainThread:50375 [wandb_run.py:_append_summary():2102] rendering summary
+2022-05-05 16:31:29,984 INFO    MainThread:50375 [wandb_run.py:_append_files():2194] logging synced files

wandb/run-20220504_142129-1tmxz74i/run-1tmxz74i.wandb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2baef3bd136aaa11e389d892bacb30c5787387e9c38e8dbd3aa9b4ef5fc2047d
-size 1047705346
+oid sha256:a48d6c37d8c3c4ab228d97cd5a6b8130cc17aec3c854afb79602452e30cbfe08
+size 1049011321

wandb/run-20220505_163723-urfp82ib/files/config.yaml

@@ -0,0 +1,788 @@
+wandb_version: 1
+
+_n_gpu:
+  desc: null
+  value: 1
+_name_or_path:
+  desc: null
+  value: ./
+_wandb:
+  desc: null
+  value:
+    cli_version: 0.12.10
+    framework: huggingface
+    huggingface_version: 4.19.0.dev0
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    m:
+    - 1: train/global_step
+      6:
+      - 3
+    - 1: train/train_runtime
+      5: 1
+      6:
+      - 1
+    - 1: train/train_samples_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/train_steps_per_second
+      5: 1
+      6:
+      - 1
+    - 1: train/total_flos
+      5: 1
+      6:
+      - 1
+    - 1: train/train_loss
+      5: 1
+      6:
+      - 1
+    - 1: train/epoch
+      5: 1
+      6:
+      - 1
+    python_version: 3.9.5
+    start_time: 1651768643
+    t:
+      1:
+      - 1
+      - 2
+      - 3
+      - 5
+      - 11
+      - 12
+      3:
+      - 13
+      4: 3.9.5
+      5: 0.12.10
+      6: 4.19.0.dev0
+      8:
+      - 5
+adafactor:
+  desc: null
+  value: false
+adam_beta1:
+  desc: null
+  value: 0.9
+adam_beta2:
+  desc: null
+  value: 0.999
+adam_epsilon:
+  desc: null
+  value: 1.0e-08
+add_cross_attention:
+  desc: null
+  value: false
+architectures:
+  desc: null
+  value:
+  - SpeechEncoderDecoderModel
+bad_words_ids:
+  desc: null
+  value: null
+bf16:
+  desc: null
+  value: false
+bf16_full_eval:
+  desc: null
+  value: false
+bos_token_id:
+  desc: null
+  value: null
+chunk_size_feed_forward:
+  desc: null
+  value: 0
+cross_attention_hidden_size:
+  desc: null
+  value: null
+data_seed:
+  desc: null
+  value: None
+dataloader_drop_last:
+  desc: null
+  value: false
+dataloader_num_workers:
+  desc: null
+  value: 0
+dataloader_pin_memory:
+  desc: null
+  value: true
+ddp_bucket_cap_mb:
+  desc: null
+  value: None
+ddp_find_unused_parameters:
+  desc: null
+  value: None
+debug:
+  desc: null
+  value: '[]'
+decoder:
+  desc: null
+  value:
+    _name_or_path: facebook/bart-large
+    activation_dropout: 0.1
+    activation_function: gelu
+    add_bias_logits: false
+    add_cross_attention: true
+    add_final_layer_norm: false
+    architectures:
+    - BartModel
+    attention_dropout: 0.1
+    bad_words_ids: null
+    bos_token_id: 0
+    chunk_size_feed_forward: 0
+    classif_dropout: 0.1
+    classifier_dropout: 0.0
+    cross_attention_hidden_size: null
+    d_model: 1024
+    decoder_attention_heads: 16
+    decoder_ffn_dim: 4096
+    decoder_layerdrop: 0.0
+    decoder_layers: 12
+    decoder_start_token_id: 2
+    diversity_penalty: 0.0
+    do_sample: false
+    dropout: 0.1
+    early_stopping: true
+    encoder_attention_heads: 16
+    encoder_ffn_dim: 4096
+    encoder_layerdrop: 0.0
+    encoder_layers: 12
+    encoder_no_repeat_ngram_size: 0
+    eos_token_id: 2
+    exponential_decay_length_penalty: null
+    finetuning_task: null
+    forced_bos_token_id: 0
+    forced_eos_token_id: 2
+    gradient_checkpointing: false
+    id2label:
+      '0': LABEL_0
+      '1': LABEL_1
+      '2': LABEL_2
+    init_std: 0.02
+    is_decoder: true
+    is_encoder_decoder: false
+    label2id:
+      LABEL_0: 0
+      LABEL_1: 1
+      LABEL_2: 2
+    length_penalty: 1.0
+    max_length: 20
+    max_position_embeddings: 1024
+    min_length: 0
+    model_type: bart
+    no_repeat_ngram_size: 3
+    normalize_before: false
+    num_beam_groups: 1
+    num_beams: 4
+    num_hidden_layers: 12
+    num_return_sequences: 1
+    output_attentions: false
+    output_hidden_states: false
+    output_scores: false
+    pad_token_id: 1
+    prefix: null
+    problem_type: null
+    pruned_heads: {}
+    remove_invalid_values: false
+    repetition_penalty: 1.0
+    return_dict: true
+    return_dict_in_generate: false
+    scale_embedding: false
+    sep_token_id: null
+    task_specific_params:
+      summarization:
+        length_penalty: 1.0
+        max_length: 128
+        min_length: 12
+        num_beams: 4
+      summarization_cnn:
+        length_penalty: 2.0
+        max_length: 142
+        min_length: 56
+        num_beams: 4
+      summarization_xsum:
+        length_penalty: 1.0
+        max_length: 62
+        min_length: 11
+        num_beams: 6
+    temperature: 1.0
+    tie_encoder_decoder: false
+    tie_word_embeddings: true
+    tokenizer_class: null
+    top_k: 50
+    top_p: 1.0
+    torch_dtype: null
+    torchscript: false
+    transformers_version: 4.19.0.dev0
+    typical_p: 1.0
+    use_bfloat16: false
+    use_cache: true
+    vocab_size: 50265
+decoder_start_token_id:
+  desc: null
+  value: 0
+deepspeed:
+  desc: null
+  value: None
+disable_tqdm:
+  desc: null
+  value: false
+diversity_penalty:
+  desc: null
+  value: 0.0
+do_eval:
+  desc: null
+  value: true
+do_predict:
+  desc: null
+  value: false
+do_sample:
+  desc: null
+  value: false
+do_train:
+  desc: null
+  value: true
+early_stopping:
+  desc: null
+  value: false
+encoder:
+  desc: null
+  value:
+    _name_or_path: facebook/wav2vec2-xls-r-300m
+    activation_dropout: 0.0
+    adapter_kernel_size: 3
+    adapter_stride: 2
+    add_adapter: true
+    add_cross_attention: false
+    apply_spec_augment: true
+    architectures:
+    - Wav2Vec2ForPreTraining
+    attention_dropout: 0.1
+    bad_words_ids: null
+    bos_token_id: 1
+    chunk_size_feed_forward: 0
+    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
+    cross_attention_hidden_size: null
+    ctc_loss_reduction: sum
+    ctc_zero_infinity: false
+    decoder_start_token_id: null
+    diversity_loss_weight: 0.1
+    diversity_penalty: 0.0
+    do_sample: false
+    do_stable_layer_norm: true
+    early_stopping: false
+    encoder_no_repeat_ngram_size: 0
+    eos_token_id: 2
+    exponential_decay_length_penalty: null
+    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
+    finetuning_task: null
+    forced_bos_token_id: null
+    forced_eos_token_id: null
+    gradient_checkpointing: false
+    hidden_act: gelu
+    hidden_dropout: 0.18004101365999406
+    hidden_size: 1024
+    id2label:
+      '0': LABEL_0
+      '1': LABEL_1
+    initializer_range: 0.02
+    intermediate_size: 4096
+    is_decoder: false
+    is_encoder_decoder: false
+    label2id:
+      LABEL_0: 0
+      LABEL_1: 1
+    layer_norm_eps: 1.0e-05
+    layerdrop: 0.0
+    length_penalty: 1.0
+    mask_feature_length: 10
+    mask_feature_min_masks: 0
+    mask_feature_prob: 0.0
+    mask_time_length: 10
+    mask_time_min_masks: 2
+    mask_time_prob: 0.1
+    max_length: 20
+    min_length: 0
+    model_type: wav2vec2
+    no_repeat_ngram_size: 0
+    num_adapter_layers: 3
+    num_attention_heads: 16
+    num_beam_groups: 1
+    num_beams: 1
+    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
+    num_return_sequences: 1
+    output_attentions: false
+    output_hidden_size: 1024
+    output_hidden_states: false
+    output_scores: false
+    pad_token_id: 0
+    prefix: null
+    problem_type: null
+    proj_codevector_dim: 768
+    pruned_heads: {}
+    remove_invalid_values: false
+    repetition_penalty: 1.0
+    return_dict: true
+    return_dict_in_generate: false
+    sep_token_id: null
+    task_specific_params: null
+    tdnn_dilation:
+    - 1
+    - 2
+    - 3
+    - 1
+    - 1
+    tdnn_dim:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 1500
+    tdnn_kernel:
+    - 5
+    - 3
+    - 3
+    - 1
+    - 1
+    temperature: 1.0
+    tie_encoder_decoder: false
+    tie_word_embeddings: true
+    tokenizer_class: null
+    top_k: 50
+    top_p: 1.0
+    torch_dtype: float32
+    torchscript: false
+    transformers_version: 4.19.0.dev0
+    typical_p: 1.0
+    use_bfloat16: false
+    use_weighted_layer_sum: false
+    vocab_size: 32
+    xvector_output_dim: 512
+encoder_no_repeat_ngram_size:
+  desc: null
+  value: 0
+eos_token_id:
+  desc: null
+  value: 2
+eval_accumulation_steps:
+  desc: null
+  value: None
+eval_batch_size:
+  desc: null
+  value: 8
+eval_delay:
+  desc: null
+  value: 0
+eval_split_name:
+  desc: null
+  value: test
+eval_steps:
+  desc: null
+  value: 500
+evaluation_strategy:
+  desc: null
+  value: steps
+exponential_decay_length_penalty:
+  desc: null
+  value: null
+finetuning_task:
+  desc: null
+  value: null
+forced_bos_token_id:
+  desc: null
+  value: null
+forced_eos_token_id:
+  desc: null
+  value: null
+fp16:
+  desc: null
+  value: true
+fp16_backend:
+  desc: null
+  value: auto
+fp16_full_eval:
+  desc: null
+  value: false
+fp16_opt_level:
+  desc: null
+  value: O1
+generation_max_length:
+  desc: null
+  value: 40
+generation_num_beams:
+  desc: null
+  value: 1
+gradient_accumulation_steps:
+  desc: null
+  value: 8
+gradient_checkpointing:
+  desc: null
+  value: true
+greater_is_better:
+  desc: null
+  value: true
+group_by_length:
+  desc: null
+  value: true
+half_precision_backend:
+  desc: null
+  value: amp
+hidden_dropout:
+  desc: null
+  value: 0.18004101365999406
+hub_model_id:
+  desc: null
+  value: None
+hub_private_repo:
+  desc: null
+  value: false
+hub_strategy:
+  desc: null
+  value: every_save
+hub_token:
+  desc: null
+  value: <HUB_TOKEN>
+id2label:
+  desc: null
+  value:
+    '0': LABEL_0
+    '1': LABEL_1
+ignore_data_skip:
+  desc: null
+  value: false
+include_inputs_for_metrics:
+  desc: null
+  value: false
+is_decoder:
+  desc: null
+  value: false
+is_encoder_decoder:
+  desc: null
+  value: true
+label2id:
+  desc: null
+  value:
+    LABEL_0: 0
+    LABEL_1: 1
+label_names:
+  desc: null
+  value: None
+label_smoothing_factor:
+  desc: null
+  value: 0.0
+language:
+  desc: null
+  value: fr.en
+learning_rate:
+  desc: null
+  value: 0.0002757119755681108
+length_column_name:
+  desc: null
+  value: length
+length_penalty:
+  desc: null
+  value: 1.0
+load_best_model_at_end:
+  desc: null
+  value: true
+local_rank:
+  desc: null
+  value: -1
+log_level:
+  desc: null
+  value: -1
+log_level_replica:
+  desc: null
+  value: -1
+log_on_each_node:
+  desc: null
+  value: true
+logging_dir:
+  desc: null
+  value: ./runs/May05_16-32-27_sanchit--v100
+logging_first_step:
+  desc: null
+  value: false
+logging_nan_inf_filter:
+  desc: null
+  value: true
+logging_steps:
+  desc: null
+  value: 1
+logging_strategy:
+  desc: null
+  value: steps
+lr_scheduler_type:
+  desc: null
+  value: linear
+max_duration_in_seconds:
+  desc: null
+  value: 20
+max_grad_norm:
+  desc: null
+  value: 1.0
+max_length:
+  desc: null
+  value: 40
+max_steps:
+  desc: null
+  value: -1
+metric_for_best_model:
+  desc: null
+  value: bleu
+min_length:
+  desc: null
+  value: 0
+model_name_or_path:
+  desc: null
+  value: ./
+model_type:
+  desc: null
+  value: speech-encoder-decoder
+mp_parameters:
+  desc: null
+  value: ''
+no_cuda:
+  desc: null
+  value: false
+no_repeat_ngram_size:
+  desc: null
+  value: 0
+num_beam_groups:
+  desc: null
+  value: 1
+num_beams:
+  desc: null
+  value: 1
+num_return_sequences:
+  desc: null
+  value: 1
+num_train_epochs:
+  desc: null
+  value: 3
+optim:
+  desc: null
+  value: adamw_hf
+output_attentions:
+  desc: null
+  value: false
+output_dir:
+  desc: null
+  value: ./
+output_hidden_states:
+  desc: null
+  value: false
+output_scores:
+  desc: null
+  value: false
+overwrite_output_dir:
+  desc: null
+  value: true
+pad_token_id:
+  desc: null
+  value: 1
+past_index:
+  desc: null
+  value: -1
+per_device_eval_batch_size:
+  desc: null
+  value: 8
+per_device_train_batch_size:
+  desc: null
+  value: 8
+per_gpu_eval_batch_size:
+  desc: null
+  value: None
+per_gpu_train_batch_size:
+  desc: null
+  value: None
+predict_with_generate:
+  desc: null
+  value: true
+prediction_loss_only:
+  desc: null
+  value: false
+prefix:
+  desc: null
+  value: null
+problem_type:
+  desc: null
+  value: null
+processor_class:
+  desc: null
+  value: Wav2Vec2Processor
+pruned_heads:
+  desc: null
+  value: {}
+push_to_hub:
+  desc: null
+  value: true
+push_to_hub_model_id:
+  desc: null
+  value: None
+push_to_hub_organization:
+  desc: null
+  value: None
+push_to_hub_token:
+  desc: null
+  value: <PUSH_TO_HUB_TOKEN>
+remove_invalid_values:
+  desc: null
+  value: false
+remove_unused_columns:
+  desc: null
+  value: true
+repetition_penalty:
+  desc: null
+  value: 1.0
+report_to:
+  desc: null
+  value: '[''tensorboard'', ''wandb'', ''codecarbon'']'
+resume_from_checkpoint:
+  desc: null
+  value: None
+return_dict:
+  desc: null
+  value: true
+return_dict_in_generate:
+  desc: null
+  value: false
+run_name:
+  desc: null
+  value: ./
+save_on_each_node:
+  desc: null
+  value: false
+save_steps:
+  desc: null
+  value: 500
+save_strategy:
+  desc: null
+  value: steps
+save_total_limit:
+  desc: null
+  value: None
+seed:
+  desc: null
+  value: 42
+sep_token_id:
+  desc: null
+  value: null
+sharded_ddp:
+  desc: null
+  value: '[]'
+skip_memory_metrics:
+  desc: null
+  value: true
+sortish_sampler:
+  desc: null
+  value: false
+task:
+  desc: null
+  value: covost2
+task_specific_params:
+  desc: null
+  value: null
+temperature:
+  desc: null
+  value: 1.0
+tf32:
+  desc: null
+  value: None
+tie_encoder_decoder:
+  desc: null
+  value: false
+tie_word_embeddings:
+  desc: null
+  value: false
+tokenizer_class:
+  desc: null
+  value: null
+top_k:
+  desc: null
+  value: 50
+top_p:
+  desc: null
+  value: 1.0
+torch_dtype:
+  desc: null
+  value: torch.float32
+torchscript:
+  desc: null
+  value: false
+tpu_metrics_debug:
+  desc: null
+  value: false
+tpu_num_cores:
+  desc: null
+  value: None
+train_batch_size:
+  desc: null
+  value: 8
+transformers_version:
+  desc: null
+  value: null
+typical_p:
+  desc: null
+  value: 1.0
+use_bfloat16:
+  desc: null
+  value: false
+use_cache:
+  desc: null
+  value: false
+use_legacy_prediction_loop:
+  desc: null
+  value: false
+warmup_ratio:
+  desc: null
+  value: 0.0
+warmup_steps:
+  desc: null
+  value: 500
+weight_decay:
+  desc: null
+  value: 0.0
+xpu_backend:
+  desc: null
+  value: None

wandb/run-20220505_163723-urfp82ib/files/output.log

@@ -0,0 +1,208 @@
+wandb: WARNING Config item 'output_dir' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'evaluation_strategy' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'per_device_train_batch_size' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'per_device_eval_batch_size' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'gradient_accumulation_steps' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'learning_rate' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'num_train_epochs' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'warmup_steps' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'logging_steps' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'save_steps' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'eval_steps' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'metric_for_best_model' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'greater_is_better' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'generation_max_length' was locked by 'sweep' (ignored update).
+wandb: WARNING Config item 'generation_num_beams' was locked by 'sweep' (ignored update).
+  0%|                                                                                          | 0/9720 [00:00<?, ?it/s]
+Training completed. Do not forget to share your model on huggingface.co/models =)
+Loading best model from ./checkpoint-1000 (score: 2.4961869532998874e-13).
+{'train_runtime': 15.9016, 'train_samples_per_second': 39123.207, 'train_steps_per_second': 611.259, 'train_loss': 0.0, 'epoch': 3.0}
+  0%|                                                                                          | 0/9720 [00:10<?, ?it/s]
+Skipping the first batches: : 0it [00:15, ?it/s]                                               | 0/9720 [00:10<?, ?it/s]
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+Model weights saved in ./pytorch_model.bin
+Feature extractor saved in ./preprocessor_config.json
+Saving model checkpoint to ./
+Configuration saved in ./config.json
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+Model weights saved in ./pytorch_model.bin
+Feature extractor saved in ./preprocessor_config.json
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible
+	- Explicitly set the environment variable TOKENIZERS_PARALLELISM=(true | false)
+huggingface/tokenizers: The current process just got forked, after parallelism has already been used. Disabling parallelism to avoid deadlocks...
+To disable this warning, you can either:
+	- Avoid using `tokenizers` before the fork if possible

wandb/run-20220505_163723-urfp82ib/files/requirements.txt

@@ -0,0 +1,287 @@
+absl-py==1.0.0
+aiohttp==3.8.1
+aiosignal==1.2.0
+alembic==1.7.7
+anyio==3.5.0
+appdirs==1.4.4
+apscheduler==3.9.1
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+arrow==1.2.2
+asttokens==2.0.5
+astunparse==1.6.3
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+autopage==0.5.0
+babel==2.9.1
+backcall==0.2.0
+backoff==1.11.1
+binaryornot==0.4.4
+bitsandbytes-cuda113==0.26.0
+black==22.1.0
+bleach==4.1.0
+boto3==1.16.34
+botocore==1.19.63
+brotli==1.0.9
+cachetools==5.0.0
+certifi==2021.10.8
+cffi==1.15.0
+chardet==4.0.0
+charset-normalizer==2.0.11
+chex==0.1.0
+click==8.0.3
+cliff==3.10.1
+clldutils==3.10.1
+cmaes==0.8.2
+cmd2==2.4.0
+codecarbon==1.2.0
+colorlog==6.6.0
+cookiecutter==1.7.3
+cryptography==36.0.2
+csvw==1.11.0
+cycler==0.11.0
+dash-bootstrap-components==1.1.0
+dash-core-components==2.0.0
+dash-html-components==2.0.0
+dash-table==5.0.0
+dash==2.3.1
+datasets==2.1.1.dev0
+debugpy==1.5.1
+decorator==5.1.1
+defusedxml==0.7.1
+deprecated==1.2.13
+dill==0.3.4
+dlinfo==1.2.1
+dm-tree==0.1.6
+docker-pycreds==0.4.0
+docker==4.4.4
+entrypoints==0.4
+execnet==1.9.0
+executing==0.8.2
+faiss-cpu==1.7.2
+filelock==3.4.2
+fire==0.4.0
+flake8==4.0.1
+flask-compress==1.11
+flask==2.1.1
+flatbuffers==1.12
+flax==0.4.0
+fonttools==4.29.1
+frozenlist==1.3.0
+fsspec==2022.1.0
+fugashi==1.1.2
+gast==0.5.3
+gitdb==4.0.9
+gitpython==3.1.18
+google-auth-oauthlib==0.4.6
+google-auth==2.6.0
+google-pasta==0.2.0
+greenlet==1.1.2
+grpcio==1.43.0
+h5py==3.6.0
+hf-doc-builder==0.2.0
+huggingface-hub==0.4.0
+hypothesis==6.36.1
+idna==3.3
+importlib-metadata==4.10.1
+iniconfig==1.1.1
+ipadic==1.0.0
+ipdb==0.13.9
+ipykernel==6.8.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.5
+isodate==0.6.1
+isort==5.10.1
+itsdangerous==2.1.2
+jax==0.2.28
+jaxlib==0.1.76+cuda11.cudnn82
+jedi==0.18.1
+jinja2-time==0.2.0
+jinja2==3.0.3
+jiwer==2.3.0
+jmespath==0.10.0
+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
+keras-preprocessing==1.1.2
+keras==2.8.0
+kiwisolver==1.3.2
+kubernetes==12.0.1
+libclang==13.0.0
+librosa==0.8.1
+llvmlite==0.38.0
+mako==1.2.0
+markdown==3.3.6
+markupsafe==2.0.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mccabe==0.6.1
+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
+nltk==3.7
+notebook==6.4.8
+numba==0.55.1
+numpy==1.21.5
+oauthlib==3.2.0
+onnx==1.11.0
+onnxconverter-common==1.9.0
+opt-einsum==3.3.0
+optax==0.1.0
+optuna==2.10.0
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+parameterized==0.8.1
+parso==0.8.3
+pathspec==0.9.0
+pathtools==0.1.2
+pbr==5.8.1
+pexpect==4.8.0
+phonemizer==3.0.1
+pickleshare==0.7.5
+pillow==9.0.0
+pint==0.16.1
+pip==22.0.2
+pkg-resources==0.0.0
+plac==1.3.5
+platformdirs==2.4.1
+plotly==5.6.0
+pluggy==1.0.0
+pooch==1.6.0
+portalocker==2.0.0
+poyo==0.5.0
+prettytable==3.2.0
+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
+py-cpuinfo==8.0.0
+py==1.11.0
+pyarrow==6.0.1
+pyasn1-modules==0.2.8
+pyasn1==0.4.8
+pycodestyle==2.8.0
+pycparser==2.21
+pyctcdecode==0.3.0
+pyflakes==2.4.0
+pygments==2.11.2
+pygtrie==2.4.2
+pynvml==11.4.1
+pyopenssl==22.0.0
+pyparsing==3.0.7
+pyperclip==1.8.2
+pypng==0.0.21
+pyrsistent==0.18.1
+pytest-forked==1.4.0
+pytest-timeout==2.1.0
+pytest-xdist==2.5.0
+pytest==7.1.1
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+python-slugify==6.1.1
+pytz-deprecation-shim==0.1.0.post0
+pytz==2021.3
+pyyaml==5.4.1
+pyzmq==22.3.0
+qtconsole==5.2.2
+qtpy==2.0.1
+ray==1.11.0
+redis==4.2.2
+regex==2022.1.18
+requests-oauthlib==1.3.1
+requests==2.27.1
+resampy==0.2.2
+responses==0.18.0
+rfc3986==2.0.0
+rouge-score==0.0.4
+rsa==4.8
+s3transfer==0.3.7
+sacrebleu==1.5.1
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+segments==2.2.0
+send2trash==1.8.0
+sentencepiece==0.1.96
+sentry-sdk==1.5.6
+setuptools==44.1.1
+shortuuid==1.0.8
+sigopt==8.3.0
+six==1.16.0
+smmap==5.0.0
+sniffio==1.2.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+sqlalchemy==1.4.34
+stack-data==0.1.4
+stevedore==3.5.0
+tabulate==0.8.9
+tenacity==8.0.1
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorboard==2.8.0
+tensorboardx==2.5
+tensorflow-io-gcs-filesystem==0.24.0
+tensorflow==2.8.0
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+text-unidecode==1.3
+tf-estimator-nightly==2.8.0.dev2021122109
+tf2onnx==1.9.3
+threadpoolctl==3.1.0
+timeout-decorator==0.5.0
+timm==0.5.4
+tokenizers==0.11.4
+toml==0.10.2
+tomli==2.0.0
+toolz==0.11.2
+torch==1.10.2+cu113
+torchaudio==0.10.2+cu113
+torchvision==0.11.3
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.18.0.dev0
+typing-extensions==3.10.0.2
+tzdata==2022.1
+tzlocal==4.2
+unidic-lite==1.0.8
+unidic==1.1.0
+uritemplate==4.1.1
+urllib3==1.26.8
+wandb==0.12.10
+wasabi==0.9.1
+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
+wrapt==1.14.0
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220505_163723-urfp82ib/files/wandb-metadata.json

@@ -0,0 +1,57 @@
+{
+    "os": "Linux-5.11.0-1028-gcp-x86_64-with-glibc2.33",
+    "python": "3.9.5",
+    "heartbeatAt": "2022-05-05T16:37:27.757365",
+    "startedAt": "2022-05-05T16:37:23.056856",
+    "docker": null,
+    "gpu": "Tesla V100-SXM2-16GB",
+    "gpu_count": 2,
+    "cpu_count": 16,
+    "cuda": null,
+    "args": [
+        "--overwrite_output_dir",
+        "--freeze_feature_encoder",
+        "--gradient_checkpointing",
+        "--predict_with_generate",
+        "--fp16",
+        "--group_by_length",
+        "--do_train",
+        "--do_eval",
+        "--load_best_model_at_end",
+        "--push_to_hub",
+        "--use_auth_token",
+        "--eval_split_name=test",
+        "--eval_steps=500",
+        "--evaluation_strategy=steps",
+        "--generation_max_length=40",
+        "--generation_num_beams=1",
+        "--gradient_accumulation_steps=8",
+        "--greater_is_better=True",
+        "--hidden_dropout=0.18004101365999406",
+        "--language=fr.en",
+        "--learning_rate=0.0002757119755681108",
+        "--logging_steps=1",
+        "--max_duration_in_seconds=20",
+        "--metric_for_best_model=bleu",
+        "--model_name_or_path=./",
+        "--num_train_epochs=3",
+        "--output_dir=./",
+        "--per_device_eval_batch_size=8",
+        "--per_device_train_batch_size=8",
+        "--save_steps=500",
+        "--task=covost2",
+        "--warmup_steps=500"
+    ],
+    "state": "running",
+    "program": "/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/run_xtreme_s.py",
+    "codePath": "run_xtreme_s.py",
+    "git": {
+        "remote": "https://huggingface.co/sanchit-gandhi/xtreme_s_xlsr_2_bart_covost2_fr_en",
+        "commit": "0bc8bdedf4de182e8496246a252ccdd3add039e2"
+    },
+    "email": "sanchit@huggingface.co",
+    "root": "/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en",
+    "host": "sanchit--v100",
+    "username": "sanchit_huggingface_co",
+    "executable": "/home/sanchit_huggingface_co/gcp/bin/python3"
+}

wandb/run-20220505_163723-urfp82ib/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/train_runtime": 15.9016, "train/train_samples_per_second": 39123.207, "train/train_steps_per_second": 611.259, "train/total_flos": 0.0, "train/train_loss": 0.0, "train/epoch": 3.0, "train/global_step": 9720, "_runtime": 15, "_timestamp": 1651768658, "_step": 0}

wandb/run-20220505_163723-urfp82ib/logs/debug-internal.log

@@ -0,0 +1,63 @@
+2022-05-05 16:37:24,392 INFO    MainThread:65310 [internal.py:wandb_internal():89] W&B internal server running at pid: 65310, started at: 2022-05-05 16:37:24.391844
+2022-05-05 16:37:24,395 DEBUG   SenderThread:65310 [sender.py:send():235] send: header
+2022-05-05 16:37:24,395 INFO    WriterThread:65310 [datastore.py:open_for_write():77] open: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/run-urfp82ib.wandb
+2022-05-05 16:37:24,395 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: check_version
+2022-05-05 16:37:24,396 DEBUG   SenderThread:65310 [sender.py:send_request():249] send_request: check_version
+2022-05-05 16:37:24,469 DEBUG   SenderThread:65310 [sender.py:send():235] send: run
+2022-05-05 16:37:24,560 INFO    SenderThread:65310 [dir_watcher.py:__init__():169] watching files in: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files
+2022-05-05 16:37:24,561 INFO    SenderThread:65310 [sender.py:_start_run_threads():809] run started: urfp82ib with start time 1651768643
+2022-05-05 16:37:24,561 DEBUG   SenderThread:65310 [sender.py:send():235] send: summary
+2022-05-05 16:37:24,561 INFO    SenderThread:65310 [sender.py:_save_file():944] saving file wandb-summary.json with policy end
+2022-05-05 16:37:24,562 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: run_start
+2022-05-05 16:37:25,562 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/wandb-summary.json
+2022-05-05 16:37:27,757 DEBUG   HandlerThread:65310 [meta.py:__init__():36] meta init
+2022-05-05 16:37:27,757 DEBUG   HandlerThread:65310 [meta.py:__init__():50] meta init done
+2022-05-05 16:37:27,757 DEBUG   HandlerThread:65310 [meta.py:probe():210] probe
+2022-05-05 16:37:27,763 DEBUG   HandlerThread:65310 [meta.py:_setup_git():200] setup git
+2022-05-05 16:37:27,796 DEBUG   HandlerThread:65310 [meta.py:_setup_git():207] setup git done
+2022-05-05 16:37:27,797 DEBUG   HandlerThread:65310 [meta.py:_save_pip():54] save pip
+2022-05-05 16:37:27,797 DEBUG   HandlerThread:65310 [meta.py:_save_pip():68] save pip done
+2022-05-05 16:37:27,798 DEBUG   HandlerThread:65310 [meta.py:probe():248] probe done
+2022-05-05 16:37:27,803 DEBUG   SenderThread:65310 [sender.py:send():235] send: files
+2022-05-05 16:37:27,804 INFO    SenderThread:65310 [sender.py:_save_file():944] saving file wandb-metadata.json with policy now
+2022-05-05 16:37:27,810 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:37:27,810 DEBUG   SenderThread:65310 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:37:27,844 DEBUG   SenderThread:65310 [sender.py:send():235] send: config
+2022-05-05 16:37:27,845 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:27,845 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:27,845 WARNING SenderThread:65310 [sender.py:send_metric():902] Seen metric with glob (shouldnt happen)
+2022-05-05 16:37:28,059 INFO    Thread-11 :65310 [upload_job.py:push():137] Uploaded file /tmp/tmp1h8vnyd5wandb/1lwnw59n-wandb-metadata.json
+2022-05-05 16:37:28,600 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/wandb-metadata.json
+2022-05-05 16:37:28,600 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/requirements.txt
+2022-05-05 16:37:28,601 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_created():217] file/dir created: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:37:30,601 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:37:32,602 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: metric
+2022-05-05 16:37:38,641 DEBUG   SenderThread:65310 [sender.py:send():235] send: history
+2022-05-05 16:37:38,642 DEBUG   SenderThread:65310 [sender.py:send():235] send: summary
+2022-05-05 16:37:38,643 INFO    SenderThread:65310 [sender.py:_save_file():944] saving file wandb-summary.json with policy end
+2022-05-05 16:37:39,604 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/wandb-summary.json
+2022-05-05 16:37:40,605 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:37:42,856 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:37:42,856 DEBUG   SenderThread:65310 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:37:52,609 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:37:55,611 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/config.yaml
+2022-05-05 16:37:56,176 DEBUG   SenderThread:65310 [sender.py:send():235] send: stats
+2022-05-05 16:37:57,896 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:37:57,896 DEBUG   SenderThread:65310 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:38:04,614 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:38:12,927 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:38:12,928 DEBUG   SenderThread:65310 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:38:22,621 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:38:24,622 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:38:26,570 DEBUG   SenderThread:65310 [sender.py:send():235] send: stats
+2022-05-05 16:38:26,622 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:38:28,216 DEBUG   HandlerThread:65310 [handler.py:handle_request():131] handle_request: stop_status
+2022-05-05 16:38:28,216 DEBUG   SenderThread:65310 [sender.py:send_request():249] send_request: stop_status
+2022-05-05 16:38:28,624 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log
+2022-05-05 16:38:30,624 INFO    Thread-8  :65310 [dir_watcher.py:_on_file_modified():230] file/dir modified: /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/files/output.log

wandb/run-20220505_163723-urfp82ib/logs/debug.log

@@ -0,0 +1,28 @@
+2022-05-05 16:37:23,058 INFO    MainThread:65172 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
+2022-05-05 16:37:23,058 INFO    MainThread:65172 [wandb_setup.py:_flush():75] Loading settings from wandb/settings
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_setup.py:_flush():75] Loading settings from environment variables: {'entity': 'sanchit-gandhi', 'project': 'xtreme_s_xlsr_2_bart_covost2_fr_en', 'sweep_id': 'pvyx3mpp', 'root_dir': '/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en', 'run_id': 'urfp82ib', 'sweep_param_path': '/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/sweep-pvyx3mpp/config-urfp82ib.yaml'}
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_setup.py:_flush():75] Inferring run settings from compute environment: {'program_relpath': 'run_xtreme_s.py', 'program': '/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/run_xtreme_s.py'}
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/logs/debug.log
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220505_163723-urfp82ib/logs/debug-internal.log
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_init.py:init():420] calling init triggers
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_init.py:init():425] wandb.init called with sweep_config: {'eval_split_name': 'test', 'eval_steps': 500, 'evaluation_strategy': 'steps', 'generation_max_length': 40, 'generation_num_beams': 1, 'gradient_accumulation_steps': 8, 'greater_is_better': True, 'hidden_dropout': 0.18004101365999406, 'language': 'fr.en', 'learning_rate': 0.0002757119755681108, 'logging_steps': 1, 'max_duration_in_seconds': 20, 'metric_for_best_model': 'bleu', 'model_name_or_path': './', 'num_train_epochs': 3, 'output_dir': './', 'per_device_eval_batch_size': 8, 'per_device_train_batch_size': 8, 'save_steps': 500, 'task': 'covost2', 'warmup_steps': 500}
+config: {}
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [wandb_init.py:init():471] starting backend
+2022-05-05 16:37:23,059 INFO    MainThread:65172 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-05-05 16:37:23,142 INFO    MainThread:65172 [backend.py:ensure_launched():219] starting backend process...
+2022-05-05 16:37:23,224 INFO    MainThread:65172 [backend.py:ensure_launched():224] started backend process with pid: 65310
+2022-05-05 16:37:23,226 INFO    MainThread:65172 [wandb_init.py:init():480] backend started and connected
+2022-05-05 16:37:23,229 INFO    MainThread:65172 [wandb_run.py:_config_callback():966] config_cb None None {'eval_split_name': 'test', 'eval_steps': 500, 'evaluation_strategy': 'steps', 'generation_max_length': 40, 'generation_num_beams': 1, 'gradient_accumulation_steps': 8, 'greater_is_better': True, 'hidden_dropout': 0.18004101365999406, 'language': 'fr.en', 'learning_rate': 0.0002757119755681108, 'logging_steps': 1, 'max_duration_in_seconds': 20, 'metric_for_best_model': 'bleu', 'model_name_or_path': './', 'num_train_epochs': 3, 'output_dir': './', 'per_device_eval_batch_size': 8, 'per_device_train_batch_size': 8, 'save_steps': 500, 'task': 'covost2', 'warmup_steps': 500}
+2022-05-05 16:37:23,244 INFO    MainThread:65172 [wandb_init.py:init():550] updated telemetry
+2022-05-05 16:37:23,438 INFO    MainThread:65172 [wandb_init.py:init():581] communicating current version
+2022-05-05 16:37:24,467 INFO    MainThread:65172 [wandb_init.py:init():586] got version response upgrade_message: "wandb version 0.12.16 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2022-05-05 16:37:24,467 INFO    MainThread:65172 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
+2022-05-05 16:37:24,561 INFO    MainThread:65172 [wandb_init.py:init():624] starting run threads in backend
+2022-05-05 16:37:27,809 INFO    MainThread:65172 [wandb_run.py:_console_start():1827] atexit reg
+2022-05-05 16:37:27,810 INFO    MainThread:65172 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
+2022-05-05 16:37:27,811 INFO    MainThread:65172 [wandb_run.py:_redirect():1706] Redirecting console.
+2022-05-05 16:37:27,812 INFO    MainThread:65172 [wandb_run.py:_redirect():1762] Redirects installed.
+2022-05-05 16:37:27,812 INFO    MainThread:65172 [wandb_init.py:init():651] run started, returning control to user process
+2022-05-05 16:37:27,815 INFO    MainThread:65172 [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': 40, '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': ['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': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50265, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, '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': True, 'num_beams': 4, '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': 3, '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': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'architectures': ['BartModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'length_penalty': 1.0, 'max_length': 128, 'min_length': 12, 'num_beams': 4}, 'summarization_cnn': {'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'num_beams': 4}, 'summarization_xsum': {'length_penalty': 1.0, 'max_length': 62, 'min_length': 11, 'num_beams': 6}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large', 'transformers_version': '4.19.0.dev0', 'add_bias_logits': False, 'add_final_layer_norm': False, 'classif_dropout': 0.1, 'gradient_checkpointing': False, 'normalize_before': False, 'model_type': 'bart'}, 'encoder': {'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': 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-xls-r-300m', 'transformers_version': '4.19.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, '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': 0.18004101365999406, 'attention_dropout': 0.1, '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': 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': '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, 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'prediction_loss_only': False, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/May05_16-32-27_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_total_limit': 'None', '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, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, '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': 'length', 'report_to': "['tensorboard', 'wandb', 'codecarbon']", '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>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, '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, 'train_batch_size': 8, 'eval_batch_size': 8}
+2022-05-05 16:37:27,818 INFO    MainThread:65172 [wandb_watch.py:watch():43] Watching

wandb/sweep-pvyx3mpp/config-urfp82ib.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.18004101365999406
+language:
+  value: fr.en
+learning_rate:
+  value: 0.0002757119755681108
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./
+per_device_eval_batch_size:
+  value: 8
+per_device_train_batch_size:
+  value: 8
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500